{"id":235797,"date":"2017-08-19T14:27:20","date_gmt":"2017-08-19T18:27:20","guid":{"rendered":"http:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/uncategorized\/ai-is-edging-into-the-art-world-in-psychedelic-ways-smithsonian.php"},"modified":"2022-12-09T07:16:28","modified_gmt":"2022-12-09T12:16:28","slug":"ai-is-edging-into-the-art-world-in-psychedelic-ways-smithsonian","status":"publish","type":"post","link":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/artificial-intelligence\/ai-is-edging-into-the-art-world-in-psychedelic-ways-smithsonian.php","title":{"rendered":"AI Is Edging Into the Art World in Psychedelic Ways &#8211; Smithsonian"},"content":{"rendered":"<p><p>  AI is now able to synthesize new sounds from old ones, and even  compose original music<\/p>\n<p>    \"Can machines be creative?\" This question is the target    of a recent Google undertaking, dubbed Project Magenta,focused    on bringing artificial intelligence into the art world.  <\/p>\n<p>    Magenta    and other creative AI endeavors draw on the power of deep    neural networks, systems that allow computers to sort through    large amounts of data, recognizing patterns, and eventually    generating their own pictures, music and more. These networks    had previously been put to artistic use by Google for its    \"DeepDream\" project, which was designed to    visualize how neural networks think. Researchers could feed the    tool images, which it thenreinterpretedinto often abstract, and    oftentrippy, works.  <\/p>\n<p>    Last    year, Google started Project Magenta to apply what it learned    from these AI-created masterpieces to further push the limits    of computer creativity in art, music, videos and more.    Now,TheNew    York Times'Cade Metz tuned into the software    giant's recent projects to see (and hear) what's come of the    endeavor.  <\/p>\n<p>    Along with the announcement of Project Magenta last summer,    Google released the neural network's first song. The Google    team gave its algorithm four notes (C, C, G, G) to work with,    and then let the machine compose a roughly 90-second song with    a piano sound.The littleditty is upbeat, starting slow    but picking up with a drum beat added behind it as it explores    patterns using those four notes.  <\/p>\n<p>    But now, Google programmers are using those networks to    not only create new pieces of music, but new instruments. For    example, a tool calledNSynth,    has analyzed hundreds of notes played by a variety of modern    instruments, mapping out the features that makea guitar    sound like a guitar, or a trumpet sound like a trumpet. Using    these maps, users can then combine instrument characteristics    to create brandnew sound makers.  <\/p>\n<p>    A    more recent project from Google trained an algorithm with    examples of classical piano music to create a tool that can    compose its own music within the framework of classical piano    techniques, reports    MatthewHutsonforScience. While you won't    findPerformanceRNN,    as the algorithm is called, composing a symphony any time soon,    it can create short original music phrasings that are \"quite    expressive,\" as programmersIan Simon    andSageevOorewrote last month on the    Project Magenta blog. And another algorithm has been trained    from Magenta's code to be able to respond to notes that people    play with its own original snippets of music, in effect    creating a \"duet\" with an AI.  <\/p>\n<p>    Other Google algorithms have worked on edging more into the    visual art world, reportsHutson. For example, the    algorithmSketchRNNhas    analyzed thousands of examples of human drawings to teach a    computer to create basic sketches of common shapes, such    aschairs, cats and trucks.  <\/p>\n<p>    Once these models have been \"trained,\" writes Google researcher    David Ha, the computercan analyze and recreate previously    submitted drawings in original ways. It can even    correctmistakes researchers added in to make the images    appear more accurate, such as drawing a pig with four legs    instead of five.Similar to the blended instruments    ofNSynth, artists can game these models by doing things    like submitting drawings of chairs to a program that draws    cats, creating blended sketches that lie somewhere between the    shapes.  <\/p>\n<p>    Some other projects haven't worked out just    yet,Hutsonreports, such as a tool to create new    jokes. (They just weren't funny.)  <\/p>\n<p>    Google    aren't the only ones interested in artsy AI. As Metz notes,    last year, researchers at Sony trained an neural network    tocompose new songs in the styles of existing    artistseven creatinganpop    songthat resemblesa composition from the    Beatles. Another neural networkcomposed its    ownChristmas    songwhen shown a picture of a Christmas tree.  <\/p>\n<p>    Though    some people are concerned that AI could replace us all,    developers don't see these tools as ever supplanting human    creativity,Hutsonreports. But rather, these    algorithms are tools that can helpinspire and channel    imagination into new creations.  <\/p>\n<p>    Maybe one day, your muse could be a computer.  <\/p>\n<p>    Like this article?    SIGN UP for our newsletter  <\/p>\n<p><!-- Auto Generated --><\/p>\n<p>Read more:<\/p>\n<p><a target=\"_blank\" rel=\"nofollow noopener\" href=\"http:\/\/www.smithsonianmag.com\/smart-news\/how-ai-making-music-and-art-180964515\/\" title=\"AI Is Edging Into the Art World in Psychedelic Ways - Smithsonian\">AI Is Edging Into the Art World in Psychedelic Ways - Smithsonian<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"<p> AI is now able to synthesize new sounds from old ones, and even compose original music \"Can machines be creative?\" This question is the target of a recent Google undertaking, dubbed Project Magenta,focused on bringing artificial intelligence into the art world.  <a href=\"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/artificial-intelligence\/ai-is-edging-into-the-art-world-in-psychedelic-ways-smithsonian.php\">Continue reading <span class=\"meta-nav\">&rarr;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"limit_modified_date":"","last_modified_date":"","_lmt_disableupdate":"","_lmt_disable":"","footnotes":""},"categories":[13],"tags":[],"class_list":["post-235797","post","type-post","status-publish","format-standard","hentry","category-artificial-intelligence"],"modified_by":"Danzig","_links":{"self":[{"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/posts\/235797"}],"collection":[{"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/comments?post=235797"}],"version-history":[{"count":0,"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/posts\/235797\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/media?parent=235797"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/categories?post=235797"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.euvolution.com\/futurist-transhuman-news-blog\/wp-json\/wp\/v2\/tags?post=235797"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}