Tom M. Mitchell, a machine learning pioneer and Carnegie Mellon University (CMU) professor, predicted the evolution and synergy of human and machine learning. Today's Facebook News Feed is a perfect example. The News Feed is programmed to display user friend content. If a user frequently tags or writes on the wall of a particular friend, the News Feed changes its behavior to display more content from that friend.
Other machine learning applications include syntactic pattern recognition, natural language processing, search engines, computer vision and machine perception.
It's difficult to replicate human intuition in a machine, primarily because human beings often learn and execute decisions unconsciously.
Like children, machines require an extended training period when developing broad algorithms geared toward the dictation of future behavior. Training techniques include rote learning, parameter adjustment, macro-operators, chunking, explanation-based learning, clustering, mistake correction, case recording, multiple model management, back propagation, reinforcement learning and genetic algorithms.
Originally posted here:
