Monthly Archives: May 2020

Scientific study of algorithms and statistical models that computer systems use to perform tasks without explicit instructions

Machine learning (ML) is the study of computer algorithms that improve automatically through experience.[1] It is seen as a subset of artificial intelligence. Machine learning algorithms build a mathematical model based on sample data, known as "training data", in order to make predictions or decisions without being explicitly programmed to do so.[2][3]:2 Machine learning algorithms are used in a wide variety of applications, such as email filtering and computer vision, where it is difficult or infeasible to develop conventional algorithms to perform the needed tasks.

Machine learning is closely related to computational statistics, which focuses on making predictions using computers. The study of mathematical optimization delivers methods, theory and application domains to the field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis through unsupervised learning.[4][5] In its application across business problems, machine learning is also referred to as predictive analytics.

Machine learning involves computers discovering how they can perform tasks without being explicitly programmed to do so. For simple tasks assigned to computers, it is possible to program algorithms telling the machine how to execute all steps required to solve the problem at hand; on the computer's part, no learning is needed. For more advanced tasks, it can be challenging for a human to manually create the needed algorithms. In practice, it can turn out to be more effective to help the machine develop its own algorithm, rather than have human programmers specify every needed step.[6][7]

The discipline of machine learning employs various approaches to help computers learn to accomplish tasks where no fully satisfactory algorithm is available. In cases where vast numbers of potential answers exist, one approach is to label some of the correct answers as valid. This can then be used as training data for the computer to improve the algorithm(s) it uses to determine correct answers. For example, to train a system for the task of digital character recognition, the MNIST dataset has often been used. [6][7]

Early classifications for machine learning approaches sometimes divided them into three broad categories, depending on the nature of the "signal" or "feedback" available to the learning system. These were:Supervised learning: The computer is presented with example inputs and their desired outputs, given by a "teacher", and the goal is to learn a general rule that maps inputs to outputs.Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means towards an end (feature learning).Reinforcement learning: A computer program interacts with a dynamic environment in which it must perform a certain goal (such as driving a vehicle or playing a game against an opponent) As it navigates its problem space, the program is provided feedback that's analogous to rewards, which it tries to maximise. [3]

Other approaches or processes have since developed that don't fit neatly into this three-fold categorisation, and sometimes more than one is used by the same machine learning system. For example topic modeling, dimensionality reduction or meta learning. [8] As of 2020, deep learning has become the dominant approach for much ongoing work in the field of machine learning . [6]

The term machine learning was coined in 1959 by Arthur Samuel, an American IBMer and pioneer in the field of computer gaming and artificial intelligence. [9][10] A representative book of the machine learning research during the 1960s was the Nilsson's book on Learning Machines, dealing mostly with machine learning for pattern classification.[11] Interest related to pattern recognition continued into the 1970s, as described by Duda and Hart in 1973. [12] In 1981 a report was given on using teaching strategies so that a neural network learns to recognize 40 characters (26 letters, 10 digits, and 4 special symbols) from a computer terminal. [13]

Tom M. Mitchell provided a widely quoted, more formal definition of the algorithms studied in the machine learning field: "A computer program is said to learn from experience E with respect to some class of tasks T and performance measure P if its performance at tasks in T, as measured by P, improves with experience E."[14] This definition of the tasks in which machine learning is concerned offers a fundamentally operational definition rather than defining the field in cognitive terms. This follows Alan Turing's proposal in his paper "Computing Machinery and Intelligence", in which the question "Can machines think?" is replaced with the question "Can machines do what we (as thinking entities) can do?".[15]

As a scientific endeavor, machine learning grew out of the quest for artificial intelligence. In the early days of AI as an academic discipline, some researchers were interested in having machines learn from data. They attempted to approach the problem with various symbolic methods, as well as what were then termed "neural networks"; these were mostly perceptrons and other models that were later found to be reinventions of the generalized linear models of statistics.[16] Probabilistic reasoning was also employed, especially in automated medical diagnosis.[17]:488

However, an increasing emphasis on the logical, knowledge-based approach caused a rift between AI and machine learning. Probabilistic systems were plagued by theoretical and practical problems of data acquisition and representation.[17]:488 By 1980, expert systems had come to dominate AI, and statistics was out of favor.[18] Work on symbolic/knowledge-based learning did continue within AI, leading to inductive logic programming, but the more statistical line of research was now outside the field of AI proper, in pattern recognition and information retrieval.[17]:708710; 755 Neural networks research had been abandoned by AI and computer science around the same time. This line, too, was continued outside the AI/CS field, as "connectionism", by researchers from other disciplines including Hopfield, Rumelhart and Hinton. Their main success came in the mid-1980s with the reinvention of backpropagation.[17]:25

Machine learning, reorganized as a separate field, started to flourish in the 1990s. The field changed its goal from achieving artificial intelligence to tackling solvable problems of a practical nature. It shifted focus away from the symbolic approaches it had inherited from AI, and toward methods and models borrowed from statistics and probability theory.[18] As of 2019, many sources continue to assert that machine learning remains a sub field of AI. Yet some practitioners, for example Dr Daniel Hulme, who both teaches AI and runs a company operating in the field, argues that machine learning and AI are separate. [7][19][6]

Machine learning and data mining often employ the same methods and overlap significantly, but while machine learning focuses on prediction, based on known properties learned from the training data, data mining focuses on the discovery of (previously) unknown properties in the data (this is the analysis step of knowledge discovery in databases). Data mining uses many machine learning methods, but with different goals; on the other hand, machine learning also employs data mining methods as "unsupervised learning" or as a preprocessing step to improve learner accuracy. Much of the confusion between these two research communities (which do often have separate conferences and separate journals, ECML PKDD being a major exception) comes from the basic assumptions they work with: in machine learning, performance is usually evaluated with respect to the ability to reproduce known knowledge, while in knowledge discovery and data mining (KDD) the key task is the discovery of previously unknown knowledge. Evaluated with respect to known knowledge, an uninformed (unsupervised) method will easily be outperformed by other supervised methods, while in a typical KDD task, supervised methods cannot be used due to the unavailability of training data.

Machine learning also has intimate ties to optimization: many learning problems are formulated as minimization of some loss function on a training set of examples. Loss functions express the discrepancy between the predictions of the model being trained and the actual problem instances (for example, in classification, one wants to assign a label to instances, and models are trained to correctly predict the pre-assigned labels of a set of examples). The difference between the two fields arises from the goal of generalization: while optimization algorithms can minimize the loss on a training set, machine learning is concerned with minimizing the loss on unseen samples.[20]

Machine learning and statistics are closely related fields in terms of methods, but distinct in their principal goal: statistics draws population inferences from a sample, while machine learning finds generalizable predictive patterns.[21] According to Michael I. Jordan, the ideas of machine learning, from methodological principles to theoretical tools, have had a long pre-history in statistics.[22] He also suggested the term data science as a placeholder to call the overall field.[22]

Leo Breiman distinguished two statistical modeling paradigms: data model and algorithmic model,[23] wherein "algorithmic model" means more or less the machine learning algorithms like Random forest.

Some statisticians have adopted methods from machine learning, leading to a combined field that they call statistical learning.[24]

A core objective of a learner is to generalize from its experience.[3][25] Generalization in this context is the ability of a learning machine to perform accurately on new, unseen examples/tasks after having experienced a learning data set. The training examples come from some generally unknown probability distribution (considered representative of the space of occurrences) and the learner has to build a general model about this space that enables it to produce sufficiently accurate predictions in new cases.

The computational analysis of machine learning algorithms and their performance is a branch of theoretical computer science known as computational learning theory. Because training sets are finite and the future is uncertain, learning theory usually does not yield guarantees of the performance of algorithms. Instead, probabilistic bounds on the performance are quite common. The biasvariance decomposition is one way to quantify generalization error.

For the best performance in the context of generalization, the complexity of the hypothesis should match the complexity of the function underlying the data. If the hypothesis is less complex than the function, then the model has under fitted the data. If the complexity of the model is increased in response, then the training error decreases. But if the hypothesis is too complex, then the model is subject to overfitting and generalization will be poorer.[26]

In addition to performance bounds, learning theorists study the time complexity and feasibility of learning. In computational learning theory, a computation is considered feasible if it can be done in polynomial time. There are two kinds of time complexity results. Positive results show that a certain class of functions can be learned in polynomial time. Negative results show that certain classes cannot be learned in polynomial time.

The types of machine learning algorithms differ in their approach, the type of data they input and output, and the type of task or problem that they are intended to solve.

Supervised learning algorithms build a mathematical model of a set of data that contains both the inputs and the desired outputs.[27] The data is known as training data, and consists of a set of training examples. Each training example has one or more inputs and the desired output, also known as a supervisory signal. In the mathematical model, each training example is represented by an array or vector, sometimes called a feature vector, and the training data is represented by a matrix. Through iterative optimization of an objective function, supervised learning algorithms learn a function that can be used to predict the output associated with new inputs.[28] An optimal function will allow the algorithm to correctly determine the output for inputs that were not a part of the training data. An algorithm that improves the accuracy of its outputs or predictions over time is said to have learned to perform that task.[14]

Types of supervised learning algorithms include Active learning , classification and regression.[29] Classification algorithms are used when the outputs are restricted to a limited set of values, and regression algorithms are used when the outputs may have any numerical value within a range. As an example, for a classification algorithm that filters emails, the input would be an incoming email, and the output would be the name of the folder in which to file the email.

Similarity learning is an area of supervised machine learning closely related to regression and classification, but the goal is to learn from examples using a similarity function that measures how similar or related two objects are. It has applications in ranking, recommendation systems, visual identity tracking, face verification, and speaker verification.

Unsupervised learning algorithms take a set of data that contains only inputs, and find structure in the data, like grouping or clustering of data points. The algorithms, therefore, learn from test data that has not been labeled, classified or categorized. Instead of responding to feedback, unsupervised learning algorithms identify commonalities in the data and react based on the presence or absence of such commonalities in each new piece of data. A central application of unsupervised learning is in the field of density estimation in statistics, such as finding the probability density function.[30] Though unsupervised learning encompasses other domains involving summarizing and explaining data features.

Cluster analysis is the assignment of a set of observations into subsets (called clusters) so that observations within the same cluster are similar according to one or more predesignated criteria, while observations drawn from different clusters are dissimilar. Different clustering techniques make different assumptions on the structure of the data, often defined by some similarity metric and evaluated, for example, by internal compactness, or the similarity between members of the same cluster, and separation, the difference between clusters. Other methods are based on estimated density and graph connectivity.

Semi-supervised learning falls between unsupervised learning (without any labeled training data) and supervised learning (with completely labeled training data). Some of the training examples are missing training labels, yet many machine-learning researchers have found that unlabeled data, when used in conjunction with a small amount of labeled data, can produce a considerable improvement in learning accuracy.

In weakly supervised learning, the training labels are noisy, limited, or imprecise; however, these labels are often cheaper to obtain, resulting in larger effective training sets.[31]

Reinforcement learning is an area of machine learning concerned with how software agents ought to take actions in an environment so as to maximize some notion of cumulative reward. Due to its generality, the field is studied in many other disciplines, such as game theory, control theory, operations research, information theory, simulation-based optimization, multi-agent systems, swarm intelligence, statistics and genetic algorithms. In machine learning, the environment is typically represented as a Markov Decision Process (MDP). Many reinforcement learning algorithms use dynamic programming techniques.[32] Reinforcement learning algorithms do not assume knowledge of an exact mathematical model of the MDP, and are used when exact models are infeasible. Reinforcement learning algorithms are used in autonomous vehicles or in learning to play a game against a human opponent.

Self-learning as machine learning paradigm was introduced in 1982 along with a neural network capable of self-learning named Crossbar Adaptive Array (CAA). [33] It is a learning with no external rewards and no external teacher advices. The CAA self-learning algorithm computes, in a crossbar fashion, both decisions about actions and emotions (feelings) about consequence situations. The system is driven by the interaction between cognition and emotion. [34]The self-learning algorithm updates a memory matrix W =||w(a,s)|| such that in each iteration executes the following machine learning routine:

It is a system with only one input, situation s, and only one output, action (or behavior) a. There is neither a separate reinforcement input nor an advice input from the environment. The backpropagated value (secondary reinforcement) is the emotion toward the consequence situation. The CAA exists in two environments, one is behavioral environment where it behaves, and the other is genetic environment, wherefrom it initially and only once receives initial emotions about situations to be encountered in the behavioral environment. After receiving the genome (species) vector from the genetic environment, the CAA learns a goal seeking behavior, in an environment that contains both desirable and undesirable situations. [35]

Several learning algorithms aim at discovering better representations of the inputs provided during training.[36] Classic examples include principal components analysis and cluster analysis. Feature learning algorithms, also called representation learning algorithms, often attempt to preserve the information in their input but also transform it in a way that makes it useful, often as a pre-processing step before performing classification or predictions. This technique allows reconstruction of the inputs coming from the unknown data-generating distribution, while not being necessarily faithful to configurations that are implausible under that distribution. This replaces manual feature engineering, and allows a machine to both learn the features and use them to perform a specific task.

Feature learning can be either supervised or unsupervised. In supervised feature learning, features are learned using labeled input data. Examples include artificial neural networks, multilayer perceptrons, and supervised dictionary learning. In unsupervised feature learning, features are learned with unlabeled input data. Examples include dictionary learning, independent component analysis, autoencoders, matrix factorization[37] and various forms of clustering.[38][39][40]

Manifold learning algorithms attempt to do so under the constraint that the learned representation is low-dimensional. Sparse coding algorithms attempt to do so under the constraint that the learned representation is sparse, meaning that the mathematical model has many zeros. Multilinear subspace learning algorithms aim to learn low-dimensional representations directly from tensor representations for multidimensional data, without reshaping them into higher-dimensional vectors.[41] Deep learning algorithms discover multiple levels of representation, or a hierarchy of features, with higher-level, more abstract features defined in terms of (or generating) lower-level features. It has been argued that an intelligent machine is one that learns a representation that disentangles the underlying factors of variation that explain the observed data.[42]

Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process. However, real-world data such as images, video, and sensory data has not yielded to attempts to algorithmically define specific features. An alternative is to discover such features or representations through examination, without relying on explicit algorithms.

Sparse dictionary learning is a feature learning method where a training example is represented as a linear combination of basis functions, and is assumed to be a sparse matrix. The method is strongly NP-hard and difficult to solve approximately.[43] A popular heuristic method for sparse dictionary learning is the K-SVD algorithm. Sparse dictionary learning has been applied in several contexts. In classification, the problem is to determine the class to which a previously unseen training example belongs. For a dictionary where each class has already been built, a new training example is associated with the class that is best sparsely represented by the corresponding dictionary. Sparse dictionary learning has also been applied in image de-noising. The key idea is that a clean image patch can be sparsely represented by an image dictionary, but the noise cannot.[44]

In data mining, anomaly detection, also known as outlier detection, is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of the data.[45] Typically, the anomalous items represent an issue such as bank fraud, a structural defect, medical problems or errors in a text. Anomalies are referred to as outliers, novelties, noise, deviations and exceptions.[46]

In particular, in the context of abuse and network intrusion detection, the interesting objects are often not rare objects, but unexpected bursts in activity. This pattern does not adhere to the common statistical definition of an outlier as a rare object, and many outlier detection methods (in particular, unsupervised algorithms) will fail on such data, unless it has been aggregated appropriately. Instead, a cluster analysis algorithm may be able to detect the micro-clusters formed by these patterns.[47]

Three broad categories of anomaly detection techniques exist.[48] Unsupervised anomaly detection techniques detect anomalies in an unlabeled test data set under the assumption that the majority of the instances in the data set are normal, by looking for instances that seem to fit least to the remainder of the data set. Supervised anomaly detection techniques require a data set that has been labeled as "normal" and "abnormal" and involves training a classifier (the key difference to many other statistical classification problems is the inherently unbalanced nature of outlier detection). Semi-supervised anomaly detection techniques construct a model representing normal behavior from a given normal training data set and then test the likelihood of a test instance to be generated by the model.

In developmental robotics, robot learning algorithms generate their own sequences of learning experiences, also known as a curriculum, to cumulatively acquire new skills through self-guided exploration and social interaction with humans. These robots use guidance mechanisms such as active learning, maturation, motor synergies and imitation.

Association rule learning is a rule-based machine learning method for discovering relationships between variables in large databases. It is intended to identify strong rules discovered in databases using some measure of "interestingness".[49]

Rule-based machine learning is a general term for any machine learning method that identifies, learns, or evolves "rules" to store, manipulate or apply knowledge. The defining characteristic of a rule-based machine learning algorithm is the identification and utilization of a set of relational rules that collectively represent the knowledge captured by the system. This is in contrast to other machine learning algorithms that commonly identify a singular model that can be universally applied to any instance in order to make a prediction.[50] Rule-based machine learning approaches include learning classifier systems, association rule learning, and artificial immune systems.

Based on the concept of strong rules, Rakesh Agrawal, Tomasz Imieliski and Arun Swami introduced association rules for discovering regularities between products in large-scale transaction data recorded by point-of-sale (POS) systems in supermarkets.[51] For example, the rule { o n i o n s , p o t a t o e s } { b u r g e r } {displaystyle {mathrm {onions,potatoes} }Rightarrow {mathrm {burger} }} found in the sales data of a supermarket would indicate that if a customer buys onions and potatoes together, they are likely to also buy hamburger meat. Such information can be used as the basis for decisions about marketing activities such as promotional pricing or product placements. In addition to market basket analysis, association rules are employed today in application areas including Web usage mining, intrusion detection, continuous production, and bioinformatics. In contrast with sequence mining, association rule learning typically does not consider the order of items either within a transaction or across transactions.

Learning classifier systems (LCS) are a family of rule-based machine learning algorithms that combine a discovery component, typically a genetic algorithm, with a learning component, performing either supervised learning, reinforcement learning, or unsupervised learning. They seek to identify a set of context-dependent rules that collectively store and apply knowledge in a piecewise manner in order to make predictions.[52]

Inductive logic programming (ILP) is an approach to rule-learning using logic programming as a uniform representation for input examples, background knowledge, and hypotheses. Given an encoding of the known background knowledge and a set of examples represented as a logical database of facts, an ILP system will derive a hypothesized logic program that entails all positive and no negative examples. Inductive programming is a related field that considers any kind of programming languages for representing hypotheses (and not only logic programming), such as functional programs.

Inductive logic programming is particularly useful in bioinformatics and natural language processing. Gordon Plotkin and Ehud Shapiro laid the initial theoretical foundation for inductive machine learning in a logical setting.[53][54][55] Shapiro built their first implementation (Model Inference System) in 1981: a Prolog program that inductively inferred logic programs from positive and negative examples.[56] The term inductive here refers to philosophical induction, suggesting a theory to explain observed facts, rather than mathematical induction, proving a property for all members of a well-ordered set.

Performing machine learning involves creating a model, which is trained on some training data and then can process additional data to make predictions. Various types of models have been used and researched for machine learning systems.

Artificial neural networks (ANNs), or connectionist systems, are computing systems vaguely inspired by the biological neural networks that constitute animal brains. Such systems "learn" to perform tasks by considering examples, generally without being programmed with any task-specific rules.

An ANN is a model based on a collection of connected units or nodes called "artificial neurons", which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit information, a "signal", from one artificial neuron to another. An artificial neuron that receives a signal can process it and then signal additional artificial neurons connected to it. In common ANN implementations, the signal at a connection between artificial neurons is a real number, and the output of each artificial neuron is computed by some non-linear function of the sum of its inputs. The connections between artificial neurons are called "edges". Artificial neurons and edges typically have a weight that adjusts as learning proceeds. The weight increases or decreases the strength of the signal at a connection. Artificial neurons may have a threshold such that the signal is only sent if the aggregate signal crosses that threshold. Typically, artificial neurons are aggregated into layers. Different layers may perform different kinds of transformations on their inputs. Signals travel from the first layer (the input layer) to the last layer (the output layer), possibly after traversing the layers multiple times.

The original goal of the ANN approach was to solve problems in the same way that a human brain would. However, over time, attention moved to performing specific tasks, leading to deviations from biology. Artificial neural networks have been used on a variety of tasks, including computer vision, speech recognition, machine translation, social network filtering, playing board and video games and medical diagnosis.

Deep learning consists of multiple hidden layers in an artificial neural network. This approach tries to model the way the human brain processes light and sound into vision and hearing. Some successful applications of deep learning are computer vision and speech recognition.[57]

Decision tree learning uses a decision tree as a predictive model to go from observations about an item (represented in the branches) to conclusions about the item's target value (represented in the leaves). It is one of the predictive modeling approaches used in statistics, data mining and machine learning. Tree models where the target variable can take a discrete set of values are called classification trees; in these tree structures, leaves represent class labels and branches represent conjunctions of features that lead to those class labels. Decision trees where the target variable can take continuous values (typically real numbers) are called regression trees. In decision analysis, a decision tree can be used to visually and explicitly represent decisions and decision making. In data mining, a decision tree describes data, but the resulting classification tree can be an input for decision making.

Support vector machines (SVMs), also known as support vector networks, are a set of related supervised learning methods used for classification and regression. Given a set of training examples, each marked as belonging to one of two categories, an SVM training algorithm builds a model that predicts whether a new example falls into one category or the other.[58] An SVM training algorithm is a non-probabilistic, binary, linear classifier, although methods such as Platt scaling exist to use SVM in a probabilistic classification setting. In addition to performing linear classification, SVMs can efficiently perform a non-linear classification using what is called the kernel trick, implicitly mapping their inputs into high-dimensional feature spaces.

Regression analysis encompasses a large variety of statistical methods to estimate the relationship between input variables and their associated features. Its most common form is linear regression, where a single line is drawn to best fit the given data according to a mathematical criterion such as ordinary least squares. The latter is often extended by regularization (mathematics) methods to mitigate overfitting and bias, as in ridge regression. When dealing with non-linear problems, go-to models include polynomial regression (for example, used for trendline fitting in Microsoft Excel [59]), Logistic regression (often used in statistical classification) or even kernel regression, which introduces non-linearity by taking advantage of the kernel trick to implicitly map input variables to higher dimensional space.

A Bayesian network, belief network or directed acyclic graphical model is a probabilistic graphical model that represents a set of random variables and their conditional independence with a directed acyclic graph (DAG). For example, a Bayesian network could represent the probabilistic relationships between diseases and symptoms. Given symptoms, the network can be used to compute the probabilities of the presence of various diseases. Efficient algorithms exist that perform inference and learning. Bayesian networks that model sequences of variables, like speech signals or protein sequences, are called dynamic Bayesian networks. Generalizations of Bayesian networks that can represent and solve decision problems under uncertainty are called influence diagrams.

A genetic algorithm (GA) is a search algorithm and heuristic technique that mimics the process of natural selection, using methods such as mutation and crossover to generate new genotypes in the hope of finding good solutions to a given problem. In machine learning, genetic algorithms were used in the 1980s and 1990s.[60][61] Conversely, machine learning techniques have been used to improve the performance of genetic and evolutionary algorithms.[62]

Usually, machine learning models require a lot of data in order for them to perform well. Usually, when training a machine learning model, one needs to collect a large, representative sample of data from a training set. Data from the training set can be as varied as a corpus of text, a collection of images, and data collected from individual users of a service. Overfitting is something to watch out for when training a machine learning model.

Federated learning is a new approach to training machine learning models that decentralizes the training process, allowing for users' privacy to be maintained by not needing to send their data to a centralized server. This also increases efficiency by decentralizing the training process to many devices. For example, Gboard uses federated machine learning to train search query prediction models on users' mobile phones without having to send individual searches back to Google.[63]

There are many applications for machine learning, including:

In 2006, the media-services provider Netflix held the first "Netflix Prize" competition to find a program to better predict user preferences and improve the accuracy on its existing Cinematch movie recommendation algorithm by at least 10%. A joint team made up of researchers from AT&T Labs-Research in collaboration with the teams Big Chaos and Pragmatic Theory built an ensemble model to win the Grand Prize in 2009 for $1million.[65] Shortly after the prize was awarded, Netflix realized that viewers' ratings were not the best indicators of their viewing patterns ("everything is a recommendation") and they changed their recommendation engine accordingly.[66] In 2010 The Wall Street Journal wrote about the firm Rebellion Research and their use of machine learning to predict the financial crisis.[67] In 2012, co-founder of Sun Microsystems, Vinod Khosla, predicted that 80% of medical doctors' jobs would be lost in the next two decades to automated machine learning medical diagnostic software.[68] In 2014, it was reported that a machine learning algorithm had been applied in the field of art history to study fine art paintings, and that it may have revealed previously unrecognized influences among artists.[69] In 2019 Springer Nature published the first research book created using machine learning.[70]

Although machine learning has been transformative in some fields, machine-learning programs often fail to deliver expected results.[71][72][73] Reasons for this are numerous: lack of (suitable) data, lack of access to the data, data bias, privacy problems, badly chosen tasks and algorithms, wrong tools and people, lack of resources, and evaluation problems.[74]

In 2018, a self-driving car from Uber failed to detect a pedestrian, who was killed after a collision.[75] Attempts to use machine learning in healthcare with the IBM Watson system failed to deliver even after years of time and billions of investment.[76][77]

Machine learning approaches in particular can suffer from different data biases. A machine learning system trained on current customers only may not be able to predict the needs of new customer groups that are not represented in the training data. When trained on man-made data, machine learning is likely to pick up the same constitutional and unconscious biases already present in society.[78] Language models learned from data have been shown to contain human-like biases.[79][80] Machine learning systems used for criminal risk assessment have been found to be biased against black people.[81][82] In 2015, Google photos would often tag black people as gorillas,[83] and in 2018 this still was not well resolved, but Google reportedly was still using the workaround to remove all gorillas from the training data, and thus was not able to recognize real gorillas at all.[84] Similar issues with recognizing non-white people have been found in many other systems.[85] In 2016, Microsoft tested a chatbot that learned from Twitter, and it quickly picked up racist and sexist language.[86] Because of such challenges, the effective use of machine learning may take longer to be adopted in other domains.[87] Concern for fairness in machine learning, that is, reducing bias in machine learning and propelling its use for human good is increasingly expressed by artificial intelligence scientists, including Fei-Fei Li, who reminds engineers that "Theres nothing artificial about AI...Its inspired by people, its created by people, andmost importantlyit impacts people. It is a powerful tool we are only just beginning to understand, and that is a profound responsibility.[88]

Classification machine learning models can be validated by accuracy estimation techniques like the Holdout method, which splits the data in a training and test set (conventionally 2/3 training set and 1/3 test set designation) and evaluates the performance of the training model on the test set. In comparison, the K-fold-cross-validation method randomly partitions the data into K subsets and then K experiments are performed each respectively considering 1 subset for evaluation and the remaining K-1 subsets for training the model. In addition to the holdout and cross-validation methods, bootstrap, which samples n instances with replacement from the dataset, can be used to assess model accuracy.[89]

In addition to overall accuracy, investigators frequently report sensitivity and specificity meaning True Positive Rate (TPR) and True Negative Rate (TNR) respectively. Similarly, investigators sometimes report the False Positive Rate (FPR) as well as the False Negative Rate (FNR). However, these rates are ratios that fail to reveal their numerators and denominators. The Total Operating Characteristic (TOC) is an effective method to express a model's diagnostic ability. TOC shows the numerators and denominators of the previously mentioned rates, thus TOC provides more information than the commonly used Receiver Operating Characteristic (ROC) and ROC's associated Area Under the Curve (AUC).[90]

Machine learning poses a host of ethical questions. Systems which are trained on datasets collected with biases may exhibit these biases upon use (algorithmic bias), thus digitizing cultural prejudices.[91] For example, using job hiring data from a firm with racist hiring policies may lead to a machine learning system duplicating the bias by scoring job applicants against similarity to previous successful applicants.[92][93] Responsible collection of data and documentation of algorithmic rules used by a system thus is a critical part of machine learning.

Because human languages contain biases, machines trained on language corpora will necessarily also learn these biases.[94][95]

Other forms of ethical challenges, not related to personal biases, are more seen in health care. There are concerns among health care professionals that these systems might not be designed in the public's interest but as income-generating machines. This is especially true in the United States where there is a long-standing ethical dilemma of improving health care, but also increasing profits. For example, the algorithms could be designed to provide patients with unnecessary tests or medication in which the algorithm's proprietary owners hold stakes. There is huge potential for machine learning in health care to provide professionals a great tool to diagnose, medicate, and even plan recovery paths for patients, but this will not happen until the personal biases mentioned previously, and these "greed" biases are addressed.[96]

Software suites containing a variety of machine learning algorithms include the following:

Originally posted here:

Machine learning - Wikipedia

What is Machine Learning?

Machine Learning is a system that can learn from example through self-improvement and without being explicitly coded by programmer. The breakthrough comes with the idea that a machine can singularly learn from the data (i.e., example) to produce accurate results.

Machine learning combines data with statistical tools to predict an output. This output is then used by corporate to makes actionable insights. Machine learning is closely related to data mining and Bayesian predictive modeling. The machine receives data as input, use an algorithm to formulate answers.

A typical machine learning tasks are to provide a recommendation. For those who have a Netflix account, all recommendations of movies or series are based on the user's historical data. Tech companies are using unsupervised learning to improve the user experience with personalizing recommendation.

Machine learning is also used for a variety of task like fraud detection, predictive maintenance, portfolio optimization, automatize task and so on.

In this basic tutorial, you will learn-

Traditional programming differs significantly from machine learning. In traditional programming, a programmer code all the rules in consultation with an expert in the industry for which software is being developed. Each rule is based on a logical foundation; the machine will execute an output following the logical statement. When the system grows complex, more rules need to be written. It can quickly become unsustainable to maintain.

Machine learning is supposed to overcome this issue. The machine learns how the input and output data are correlated and it writes a rule. The programmers do not need to write new rules each time there is new data. The algorithms adapt in response to new data and experiences to improve efficacy over time.

Machine learning is the brain where all the learning takes place. The way the machine learns is similar to the human being. Humans learn from experience. The more we know, the more easily we can predict. By analogy, when we face an unknown situation, the likelihood of success is lower than the known situation. Machines are trained the same. To make an accurate prediction, the machine sees an example. When we give the machine a similar example, it can figure out the outcome. However, like a human, if its feed a previously unseen example, the machine has difficulties to predict.

The core objective of machine learning is the learning and inference. First of all, the machine learns through the discovery of patterns. This discovery is made thanks to the data. One crucial part of the data scientist is to choose carefully which data to provide to the machine. The list of attributes used to solve a problem is called a feature vector. You can think of a feature vector as a subset of data that is used to tackle a problem.

The machine uses some fancy algorithms to simplify the reality and transform this discovery into a model. Therefore, the learning stage is used to describe the data and summarize it into a model.

For instance, the machine is trying to understand the relationship between the wage of an individual and the likelihood to go to a fancy restaurant. It turns out the machine finds a positive relationship between wage and going to a high-end restaurant: This is the model

When the model is built, it is possible to test how powerful it is on never-seen-before data. The new data are transformed into a features vector, go through the model and give a prediction. This is all the beautiful part of machine learning. There is no need to update the rules or train again the model. You can use the model previously trained to make inference on new data.

The life of Machine Learning programs is straightforward and can be summarized in the following points:

Once the algorithm gets good at drawing the right conclusions, it applies that knowledge to new sets of data.

Machine learning can be grouped into two broad learning tasks: Supervised and Unsupervised. There are many other algorithms

An algorithm uses training data and feedback from humans to learn the relationship of given inputs to a given output. For instance, a practitioner can use marketing expense and weather forecast as input data to predict the sales of cans.

You can use supervised learning when the output data is known. The algorithm will predict new data.

There are two categories of supervised learning:

Imagine you want to predict the gender of a customer for a commercial. You will start gathering data on the height, weight, job, salary, purchasing basket, etc. from your customer database. You know the gender of each of your customer, it can only be male or female. The objective of the classifier will be to assign a probability of being a male or a female (i.e., the label) based on the information (i.e., features you have collected). When the model learned how to recognize male or female, you can use new data to make a prediction. For instance, you just got new information from an unknown customer, and you want to know if it is a male or female. If the classifier predicts male = 70%, it means the algorithm is sure at 70% that this customer is a male, and 30% it is a female.

The label can be of two or more classes. The above example has only two classes, but if a classifier needs to predict object, it has dozens of classes (e.g., glass, table, shoes, etc. each object represents a class)

When the output is a continuous value, the task is a regression. For instance, a financial analyst may need to forecast the value of a stock based on a range of feature like equity, previous stock performances, macroeconomics index. The system will be trained to estimate the price of the stocks with the lowest possible error.

In unsupervised learning, an algorithm explores input data without being given an explicit output variable (e.g., explores customer demographic data to identify patterns)

You can use it when you do not know how to classify the data, and you want the algorithm to find patterns and classify the data for you

Type

K-means clustering

Puts data into some groups (k) that each contains data with similar characteristics (as determined by the model, not in advance by humans)

Clustering

Gaussian mixture model

A generalization of k-means clustering that provides more flexibility in the size and shape of groups (clusters

Clustering

Hierarchical clustering

Splits clusters along a hierarchical tree to form a classification system.

Can be used for Cluster loyalty-card customer

Clustering

Recommender system

Help to define the relevant data for making a recommendation.

Clustering

PCA/T-SNE

Mostly used to decrease the dimensionality of the data. The algorithms reduce the number of features to 3 or 4 vectors with the highest variances.

Dimension Reduction

There are plenty of machine learning algorithms. The choice of the algorithm is based on the objective.

In the example below, the task is to predict the type of flower among the three varieties. The predictions are based on the length and the width of the petal. The picture depicts the results of ten different algorithms. The picture on the top left is the dataset. The data is classified into three categories: red, light blue and dark blue. There are some groupings. For instance, from the second image, everything in the upper left belongs to the red category, in the middle part, there is a mixture of uncertainty and light blue while the bottom corresponds to the dark category. The other images show different algorithms and how they try to classified the data.

The primary challenge of machine learning is the lack of data or the diversity in the dataset. A machine cannot learn if there is no data available. Besides, a dataset with a lack of diversity gives the machine a hard time. A machine needs to have heterogeneity to learn meaningful insight. It is rare that an algorithm can extract information when there are no or few variations. It is recommended to have at least 20 observations per group to help the machine learn. This constraint leads to poor evaluation and prediction.

Augmentation:

Automation:

Finance Industry

Government organization

Healthcare industry

Marketing

Example of application of Machine Learning in Supply Chain

Machine learning gives terrific results for visual pattern recognition, opening up many potential applications in physical inspection and maintenance across the entire supply chain network.

Unsupervised learning can quickly search for comparable patterns in the diverse dataset. In turn, the machine can perform quality inspection throughout the logistics hub, shipment with damage and wear.

For instance, IBM's Watson platform can determine shipping container damage. Watson combines visual and systems-based data to track, report and make recommendations in real-time.

In past year stock manager relies extensively on the primary method to evaluate and forecast the inventory. When combining big data and machine learning, better forecasting techniques have been implemented (an improvement of 20 to 30 % over traditional forecasting tools). In term of sales, it means an increase of 2 to 3 % due to the potential reduction in inventory costs.

Example of Machine Learning Google Car

For example, everybody knows the Google car. The car is full of lasers on the roof which are telling it where it is regarding the surrounding area. It has radar in the front, which is informing the car of the speed and motion of all the cars around it. It uses all of that data to figure out not only how to drive the car but also to figure out and predict what potential drivers around the car are going to do. What's impressive is that the car is processing almost a gigabyte a second of data.

Machine learning is the best tool so far to analyze, understand and identify a pattern in the data. One of the main ideas behind machine learning is that the computer can be trained to automate tasks that would be exhaustive or impossible for a human being. The clear breach from the traditional analysis is that machine learning can take decisions with minimal human intervention.

Take the following example; a retail agent can estimate the price of a house based on his own experience and his knowledge of the market.

A machine can be trained to translate the knowledge of an expert into features. The features are all the characteristics of a house, neighborhood, economic environment, etc. that make the price difference. For the expert, it took him probably some years to master the art of estimate the price of a house. His expertise is getting better and better after each sale.

For the machine, it takes millions of data, (i.e., example) to master this art. At the very beginning of its learning, the machine makes a mistake, somehow like the junior salesman. Once the machine sees all the example, it got enough knowledge to make its estimation. At the same time, with incredible accuracy. The machine is also able to adjust its mistake accordingly.

Most of the big company have understood the value of machine learning and holding data. McKinsey have estimated that the value of analytics ranges from $9.5 trillion to $15.4 trillion while $5 to 7 trillion can be attributed to the most advanced AI techniques.

Continued here:

Machine Learning Tutorial for Beginners - Guru99

SANTA CLARA, Calif., May 14, 2020 /PRNewswire/ --ValleyML, Valley Machine Learning and Articial Intelligence is the most active and important community of ML & AI Companies and Start-ups, Data Practitioners, Executives and Researchers. We have a global outreach to close to 200,000 professionals in AI and Machine Learning. The focus areas of our members are AI Robotics, AI in Enterprise and AI Hardware. We plan to cover the state-of-the-art advancements in AI technology.ValleyML sponsors include UL, MINDBODY Inc., Ambient Scientific Inc., SEMI, Intel, Western Digital, Texas Instruments, Google, Facebook, Cadence andXilinx.

ValleyML Machine Learning and Boot Camp -2020Build a solid foundation of Machine Learning / Deep Learning principles and apply the techniques to real-world problems. Get IEEE PDH Certificate. Virtual Live Boot Camp from July 14th-Sept 10th.Description. Enroll and Learn at ValleyML Live Learning Platform(coupons: valleyml40 Register by June 1st for 40% off. valleyml25 Register by July 1st for 25% off.)

Global Call for Presentations & Sponsors for ValleyML AI Expo 2020 conference series (Global & Virtual).A unified call for proposals from industry for ValleyML's AI Expo events focused on Hardware, Enterprise and Robotics is now open at ValleyML2020. Submit by June 1st to participate in a virtual and global series of 90-minute talks and discussions from Sept 21st to Nov 19th on Mondays-Thursdays. Sponsor AI Expo!Limited sponsorship opportunities available. These highly focused events welcome a community of CTOs, CEOs, Chief Data Scientists, product management executives and delegates from some of the world's top technology companies.

Committee for ValleyML AI Expo 2020:

Program Chair for AI Enterprise and AI Robotics series:

Mr. Marc Mar-Yohana, Vice President at UL.

Program Chair for AI Hardware series:

Mr. George Williams, Director of Data Science at GSI Technology.

General Chair:

Dr. Kiran Gunnam, Distinguished Engineer, Machine Learning and Computer Vision, Western Digital.

SOURCE ValleyML

AI Expo 2022

Go here to see the original:

ValleyML is launching a Machine Learning and Deep Learning Boot Camp from July 14th to Sept 10th and AI Expo Series from Sept 21st to Nov 19th 2020....

The chaos and uncertainty surrounding the coronavirus pandemic have claimed an unlikely victim: the machine learning systems that are programmed to make sense of our online behavior.

The algorithms that recommend products on Amazon, for instance, are struggling to interpret our new lifestyles, MIT Technology Review reports.

And while machine learning tools are built to take in new data, they're typically not so robust that they can adapt as dramatically as needed.

For instance, MIT Tech reports that a company that detects credit card fraud needed to step in and tweak its algorithm to account for a surge of interest in gardening equipment and power tools.

An online retailer found that its AI was ordering stock that no longer matched with what was selling. And a firm that uses AI to recommend investments based on sentiment analysis of news stories was confused by the generally negative tone throughout the media.

"The situation is so volatile," Rael Cline, CEO of the algorithmic marketing consulting firm Nozzle, told MIT Tech.

"You're trying to optimize for toilet paper last week, and this week everyone wants to buy puzzles or gym equipment."

While some companies are dedicating more time and resources to manually steering their algorithms, others see this as an opportunity to improve.

"A pandemic like this is a perfect trigger to build better machine-learning models," Sharma said.

READ MORE: Our weird behavior during the pandemic is messing with AI models

This article was originally published by Futurism. Read the original article.

See the article here:

Our Behaviour in This Pandemic Has Seriously Confused AI Machine Learning Systems - ScienceAlert

LAKEWOOD, Ohio, May 14, 2020 /PRNewswire/ --Onix is proud to participate in the launch of Amazon Kendra, a highly accurate and easy to use enterprise search service powered by machine learning from Amazon Web Services (AWS).

Amazon Kendra delivers powerful natural language search capabilities to customer websites and applications so their end users can more easily find the information they need. When users ask a question, Amazon Kendra uses finely tuned machine learning algorithms to understand the context and return the most relevant results, whether that be a precise answer or an entire document.

"Search capabilities have evolved over the years. Users now expect the same experience they get from the semantic and natural language search engines and conversational interfaces they use in their personal lives," notes Onix President and CEO Tim Needles. "Powered by machine learning and natural language understanding, Amazon Kendra improves employee productivity by up to 25%. With more accurate enterprise search, Amazon Kendra opens new opportunities for keyword-based on-premises and SaaS search users to migrate to the cloud and avoid contract lock-ins."

Onix has been a leader in the enterprise search space since 2002. The company provides 1:1 consulting, planning, and deployment of search solutions for hundreds of clients with a team that includes 10 certified deployment engineers. Onix has won six prestigious awards for enterprise search and boasts a 98% Customer Satisfaction Rating.

About Onix

As a leading cloud solutions provider, Onix elevates customers with consulting services for cloud infrastructure, collaboration, devices, enterprise search and geospatial technology. Onix uses its ever-evolving expertise to achieve clients' strategic cloud computing goals.

Onix backs its strategic planning and deployment with incomparable ongoing service, training and support. It also offers its own suite of standalone products to solve specific business challenges, including OnSpend, a cloud billing and budget management software solution.

Headquartered in Lakewood, Ohio, Onix serves its customers with virtual teams in major metro areas, including Atlanta, Austin, San Francisco, Boston, Chicago and New York. Onix also has Canadian offices in Toronto, Montreal and Ottawa. Learn more at http://www.onixnet.com.

Contact: Robin SuttellOnix216-801-4984robin@onixnet.com

Original post:

Onix To Help Organizations Uncover the Power of Machine Learning-Driven Search With Amazon Kendra - News-Herald.com

From navigating to a new place to picking out new music, algorithms have laid the foundation for large parts of modern life. Similarly, artificial Intelligence is booming because it automates and backs so many products and applications. Recently, I addressed some analytical applications for TensorFlow. In this article, Im going to lay out a higher-level view of Googles TensorFlow deep learning framework, with the ultimate goal of helping you to understand and build deep learning algorithms from scratch.

Over the past couple of decades, deep learning has evolved rapidly, leading to massive disruption in a range of industries and organizations. The term was coined in 1943 when Warren McCulloch and Walter Pitts created a computer model based on neural networks of a human brain, creating the first artificial neural networks (or ANNs). Deep learning now denotes a branch of machine learning that deploys data-centric algorithms in real-time.

Backpropagation is a popular algorithm that has had a huge impact in the field of deep learning. It allows ANNs to learn by themselves based on the errors they generate while learning. To further enhance the scope of an ANN, architectures like Convolutional Neural Networks, Recurrent Neural Networks, and Generative Networks have come into the picture. Before we delve into them, lets first understand the basic components of a neural network.

Neurons and Artificial Neural Networks

An artificial neural network is a representational framework that extracts features from the data its given. The basic computational unit of an ANN is the neuron. Neurons are connected using artificial layers through which the information passes. As the information flows through these layers, the neural network identifies patterns between the data. This type of processing makes ANNs useful for several applications, such as for prediction and classification.

Now lets take a look at the basic structure of an ANN. It consists of three layers: the input layer, the output layer, which is always fixed or constant, and the hidden layer. Inputs initially pass through an input layer. This layer always accepts a constant set of dimensions. For instance, if we wanted to train a classifier that differentiates between dogs and cats, the inputs (in this case, images) should be of the same size. The input then passes through the hidden layers and the network updates the weights and recognizes the patterns. In the final step, we classify the data at the output layer.

Weights and Biases

Every neuron inside a neural network is associated with parameters, weight and bias. The weight is an integer that controls the signals between any two neurons. If the output is desirable, meaning that the output is in proximity to the one that we expected it to produce, then the weights are ideal. If the same network is generating an erroneous output thats far away from the actual one, then the network alters the weights to improve the subsequent results.

Bias, the other parameter, is the algorithms tendency to consistently learn the wrong thing by not taking into account all the information in the data. For the model to be accurate, bias needs to be low. If there are inconsistencies in the dataset, like missing values, fewer data tuples, or erroneous input data, the bias would be high and the predicted values could be wrong.

Working of a Neural Network

Before we get started with TensorFlow, lets examine how a neural network produces an output with weights, biases, and input by taking a look at the first neural network, called Perceptron, which dates back to 1958. The Perceptron network is a simple binary classifier. Understanding how this works will allow us to comprehend the workings of a modern neuron.

The Perceptron network is a supervised machine learning technique that uses a binary classifier function by mapping a vector of binary variables to a single binary output. It works as follows:

Multiply the inputs (x1, x2, x3) of the network to their corresponding weights (w1, w2, w3).

Add the multiplied weights and inputs together. This is called the weighted sum, denoted by, x1*w1 + x2*w2 +x3*w3

Apply the activation function. Determine whether the weighted sum is greater than a threshold (say, 0.5), if yes, assign 1 as the output, otherwise assign 0. This is a simple step function.

Of course, Perceptron is a simple neural network that doesnt wholly consider all the concepts necessary for an end-to-end neural network. Therefore, lets go over all the phases that a neural network has to go through to build a sophisticated ANN.

Input

A neural network has to be defined with the number of input dimensions, output features, and hidden units. All these metrics fall in a common basket called hyperparameters. Hyperparameters are numeric values that determine and define the neural network structure.

Weights and biases are set randomly for all neurons in the hidden layers.

Feed Forward

The data is sent into the input and hidden layers, where the weights get updated for every iteration. This creates a function that maps the input with the output data. Mathematically, it is defined asy=f(x), where y is the output, x is the input, and f is the activation function.

For every forward pass (when the data travels from the input to the output layer), the loss is calculated (actual value minus predicted value). The loss is again sent back (backpropagation) and the network is retrained using a loss function.

Output error

The loss is gradually reduced using gradient descent and loss function.

The gradient descent can be calculated with respect to any weight and bias.

Backpropagation

We backpropagate the error that traverses through each and every layer using the backpropagation algorithm.

Output

By minimizing the loss, the network re-updates the weights for every iteration (One Forward Pass plus One Backward Pass) and increases its accuracy.

As we havent yet talked about what an activation function is, Ill expand that a bit in the next section.

Activation Functions

An activation function is a core component of any neural network. It learns a non-linear, complex functional mapping between the input and the response variables or output. Its main purpose is to convert an input signal of a node in an ANN to an output signal. That output signal is the input to the subsequent layer in the stack. There are several types of activation functions available that could be used for different use cases. You can find a list comprising the most popular activation functions along with their respective mathematical formulae here.

Now that we understand what a feed forward pass looks like, lets also explore the backward propagation of errors.

Loss Function and Backpropagation

During training of a neural network, there are too many unknowns to be deciphered. As a result, calculating the ideal weights for all the nodes in a neural network is difficult. Therefore, we use an optimization function through which we could navigate the space of possible ideal weights to make good predictions with a trained neural network.

We use a gradient descent optimization algorithm wherein the weights are updated using the backpropagation of error. The term gradient in gradient descent refers to an error gradient, where the model with a given set of weights is used to make predictions and the error for those predictions is calculated. The gradient descent optimization algorithm is used to calculate the partial derivatives of the loss function (errors) with respect to any weight w and bias b. In practice, this means that the error vectors would be calculated commencing from the final layer, and then moving towards the input layer by updating the weights and biases, i.e., backpropagation. This is based on differentiations of the respective error terms along each layer. To make our lives easier, however, these loss functions and backpropagation algorithms are readily available in neural network frameworks such as TensorFlow and PyTorch.

Moreover, a hyperparameter called learning rate controls the rate of adjustment of weights of a network with respect to the gradient descent. The lower the learning rate, the slower we travel down the slope (to reach the optimum, or so-called ideal case) while calculating the loss.

TensorFlow is a powerful neural network framework that can be used to deploy high-level machine learning models into production. It was open-sourced by Google in 2015. Since then, its popularity has increased, making it a common choice for building deep learning models. On October 1st, a new, stable version got released, called TensorFlow 2.0, with a few major changes:

Eager Execution by Default - Instead of creating tf.session(), we can directly execute the code as usual Python code. In TensorFlow 1.x, we had to create a TensorFlow graph before computing any operation. In TensorFlow 2.0, however, we can build neural networks on the fly.

Keras Included - Keras is a high-level neural network built on top of TensorFlow. It is now integrated into TensorFlow 2.0 and we can directly import Keras as tf.keras, and thereby define our neural network.

TF Datasets - A lot of new datasets have been added to work and play with in a new module called tf.data.

1.0 Support: All the existing TensorFlow 1.x code can be executed using TensorFlow 2.0; we need not modify any of our previous code.

Major Documentation and API cleanup changes have also been introduced.

The TensorFlow library was built based on computational graphs a runtime for executing such computational graphs. Now, lets perform a simple operation in TensorFlow.

Here, we declared two variables a and b. We calculated the product of those two variables using a multiplication operation in Python (*) and stored the result in a variable called prod. Next, we calculated the sum of a and b and stored them in a variable named sum. Lastly, we declared the result variable that would divide the product by the sum and then would print it.

This explanation is just a Pythonic way of understanding the operation. In TensorFlow, each operation is considered as a computational graph. This is a more abstract way of describing a computer program and its computations. It helps in understanding the primitive operations and the order in which they are executed. In this case, we first multiply a and b, and only when this expression is evaluated, we take their sum. Later, we take prod and sum, and divide them to output the result.

TensorFlow Basics

To get started with TensorFlow, we should be aware of a few essentials related to computational graphs. Lets discuss them in brief:

Variables and Placeholders: TensorFlow uses the usual variables, which can be updated at any point of time, except that these need to be initialized before the graph is executed. Placeholders, on the other hand, are used to feed data into the graph from outside. Unlike variables, they dont need to be initialized.Consider a Regression equation, y = mx+c, where x and y are placeholders, and m and c are variables.

Constants and Operations: Constants are the numbers that cannot be updated. Operations represent nodes in the graph that perform computations on data.

Graph is the backbone that connects all the variables, placeholders, constants, and operators.

Prior to installing TensorFlow 2.0, its essential that you have Python on your machine. Lets look at its installation procedure.

Python for Windows

You can download it here.

Click on the Latest Python 3 release - Python x.x.x. Select the option that suits your system (32-bit - Windows x86 executable installer, or 64-bit - Windows x86-64 executable installer). After downloading the installer, follow the instructions that are displayed on the setup wizard. Make sure to add Python to your PATH using environment variables.

Python for OSX

You can download it here.

Click on the Latest Python 3 release - Python x.x.x. Select macOS 64-bit installer,and run the file.

Python on OSX can also be installed using Homebrew (package manager).

To do so, type the following commands:

Python for Debian/Ubuntu

Invoke the following commands:

This installs the latest version of Python and pip in your system.

Python for Fedora

Invoke the following commands:

This installs the latest version of Python and pip in your system.

After youve got Python, its time to install TensorFlow in your workspace.

To fetch the latest version, pip3 needs to be updated. To do so, type the command

Now, install TensorFlow 2.0.

This automatically installs the latest version of TensorFlow onto your system. The same command is also applicable to update the older version of TensorFlow.

The argument tensorflow in the above command could be any of these:

tensorflow Latest stable release (2.x) for CPU-only.

tensorflow-gpu Latest stable release with GPU support (Ubuntu and Windows).

tf-nightly Preview build (unstable). Ubuntu and Windows include GPU support.

tensorflow==1.15 The final version of TensorFlow 1.x.

To verify your install, execute the code:

Now that you have TensorFlow on your local machine, Jupyter notebooks are a handy tool for setting up the coding space. Execute the following command to install Jupyter on your system:

Now that everything is set up, lets explore the basic fundamentals of TensorFlow.

Tensors have previously been used largely in math and physics. In math, a tensor is an algebraic object that obeys certain transformation rules. It defines a mapping between objects and is similar to a matrix, although a tensor has no specific limit to its possible number of indices. In physics, a tensor has the same definition as in math, and is used to formulate and solve problems in areas like fluid mechanics and elasticity.

Although tensors were not deeply used in computer science, after the machine learning and deep learning boom, they have become heavily involved in solving data crunching problems.

Scalars

The simplest tensor is a scalar, which is a single number and is denoted as a rank-0 tensor or a 0th order tensor. A scalar has magnitude but no direction.

Vectors

A vector is an array of numbers and is denoted as a rank-1 tensor or a 1st order tensor. Vectors can be represented as either column vectors or row vectors.

A vector has both magnitude and direction. Each value in the vector gives the coordinate along a different axis, thus establishing direction. It can be depicted as an arrow; the length of the arrow represents the magnitude, and the orientation represents the direction.

Matrices

A matrix is a 2D array of numbers where each element is identified by a set of two numbers, row and column. A matrix is denoted as a rank-2 tensor or a 2nd order tensor. In simple terms, a matrix is a table of numbers.

Tensors

A tensor is a multi-dimensional array with any number of indices. Imagine a 3D array of numbers, where the data is arranged as a cube: thats a tensor. When its an nD array of numbers, that's a tensor as well. Tensors are usually used to represent complex data. When the data has many dimensions (>=3), a tensor is helpful in organizing it neatly. After initializing, a tensor of any number of dimensions can be processed to generate the desired outcomes.

TensorFlow represents tensors with ease using simple functionalities defined by the framework. Further, the mathematical operations that are usually carried out with numbers are implemented using the functions defined by TensorFlow.

Firstly, lets import TensorFlow into our workspace. To do so, invoke the following command:

This enables us to use the variable tf thereafter.

Now, lets take a quick overview of the basic operations and math, and you can simultaneously execute the code in the Jupyter playground for a better understanding of the concepts.

tf.Tensor

The primary object in TensorFlow that you play with is tf.Tensor. This is a tensor object that is associated with a value. It has two properties bound to it: data type and shape. The data type defines the type and size of data that will be consumed by a tensor. Possible types include float32, int32, string, et cetera. Shape defines the number of dimensions.

tf.Variable()

The variable constructor requires an argument which could be a tensor of any shape and type. After creating the instance, this variable is added to the TensorFlow graph and can be modified using any of the assign methods. It is declared as follows:

Output:

tf.constant()

The tensor is populated with a value, dtype, and, optionally, a shape. This value remains constant and cannot be modified further.

Follow this link:

A Lightning-Fast Introduction to Deep Learning and TensorFlow 2.0 - Built In

AUSTIN, Texas, May 14, 2020 /PRNewswire/ --SparkCognition, a leading industrial artificial intelligence (AI) company, is pleased to announce that Japanese AI and Fintech company, MILIZE Co., Ltd. will offer Japanese financial institutions fraud detection and anti-money laundering solutions. These solutions will be built using the automated machine learning software of SparkCognition.

With the enormous increase of online payment, internet banking, and QR code payments, illegal use of credit cards is on the rise. However, there are not many Japanese companies that have introduced advanced solutions for fraud detection that currently exist internationally. In addition, financial authorities and institutions around the world are expected to report strengthened measures against money laundering in August 2020. As a result, taking these steps against money laundering has become an urgent management issue in Japanese financial institutions.

At one credit card company in South America, the ratio of fraudulent use to the total transactions reached about 20%, which reduced the profitability of the business. Therefore the company introduced a fraudulent transaction detection system that utilizes the AI technology of SparkCognition, which has extensive experience working with financial service clients. Though the credit card company did not have a team of data scientists, due to the ease with which analysts on staff were able to apply SparkCognition technology, accurate machine learning models were developed, tested, and operationalized within a few short weeks. As a result, it is now possible to detect fraudulent transactions with about 90% accuracy, which has led to a significant improvement in the credit card company's profitability.

Based on SparkCognition's international success in fielding machine learning systems in financial services, MILIZE will offer a fraud detection and anti-money laundering solution, built with SparkCognition AI technology, along with consulting services, development and operational assistance to local credit card companies, banks and other financial institutions. By submitting transaction data to a MILIZE-operated cloud service, financial institutions will be able to detect suspicious transactions without making large-scale investments in self-hosted infrastructure.

MILIZE makes full use of quantitative techniques, fintech, AI, and big data, and provides a large number of operational support solutions such as risk management, performance forecast, stock price forecast, and more, to a wide range of financial institutions. SparkCognition is a leading company in the field of artificial intelligence and provides AI solutions to companies and government agencies around the world.

To learn more about SparkCognition, visit http://www.sparkcognition.com.

About SparkCognition:

With award-winning machine learning technology, a multinational footprint, and expert teams focused on defense, IIoT, and finance, SparkCognition builds artificial intelligence systems to advance the most important interests of society. Our customers are trusted with protecting and advancing lives, infrastructure, and financial systems across the globe. They turn to SparkCognition to help them analyze complex data, empower decision-making, and transform human and industrial productivity. SparkCognition offers four main products:DarwinTM, DeepArmor, SparkPredict, and DeepNLPTM. With our leading-edge artificial intelligence platforms, our clients can adapt to a rapidly changing digital landscape and accelerate their business strategies. Learn more about SparkCognition's AI applications and why we've been featured in CNBC's 2017 Disruptor 50, and recognized three years in a row on CB Insights AI 100, by visiting http://www.sparkcognition.com.

For Media Inquiries:

Michelle SaabSparkCognitionVP, Marketing Communications [emailprotected] 512-956-5491

SOURCE SparkCognition

http://sparkcognition.com

Read the original here:

SparkCognition and Milize to Offer Automated Machine Learning Solutions for Financial Institutions to the APAC Region - PRNewswire

Walmart provided more details on its new Express two-hour delivery service, piloted last month and on its way to nearly 2,000 stores.

As agility has become the key to success within a retail landscape extraordinarily disrupted by the spread of COVID-19, the company said it tested, released and scaled the initiative in just over two weeks.

As we continue to add new machine learning-driven capabilities like this in the future, as well as the corresponding customer experiences, well be able to iterate and scale quickly by leveraging the flexible technology platforms weve developed, Janey Whiteside, Walmart chief customer officer and Suresh Kumar, global technology officer and chief development officer, wrote in a company blog post.

The contactless delivery service employs machine learning to fulfill orders from nearly 2,000 stores, fulfilled by 74,000 personal shoppers. Developed by the companys in-house global technology team, the system accounts for such variables as order quantity, staffing levels, the types of delivery vehicles available, and estimated route length between a store and home.

See also: How the Coronavirus Will Shape Retail Over the Next 35 Years

It also pulls in weather data to account for delivery speeds, and Whiteside and Kumar said its consistently refining its estimates for future orders.

Consumers must pay an additional $10, on top of any other delivery charges, to take advantage of the service.

Separately. Walmartannounced it's paying out another $390 million in cash bonuses to its U.S. hourly associates as a way to recognize their efforts during the spread of COVID-19.

Full-time associates employed as of June 5 will receive $300 while part-time and temporary associates will receive $150, paid out on June 25. Associates in stores, clubs, supply chain and offices, drivers, and assistant managers in stores and clubs are all included.

Walmart and Sams Club associates continue to do remarkable work, and its important we reward and appreciate them, said John Furner, president and CEO of Walmart U.S., in a statement. All across the country, theyre providing Americans with the food, medicine and supplies they need, while going above and beyond the normal scope of their jobs diligently sanitizing their facilities, making customers and members feel safe and welcome, and handling difficult situations with professionalism and grace.

The retailer has committed more than $935 million in bonuses for associates so far this year.

See also: Walmart Expands No-Contact Transactions During COVID-19

Read the original post:

How is Walmart Express Delivery Nailing that 2-Hour Window? Machine Learning - Retail Info Systems News