{"id":110129,"date":"2020-07-18T08:02:37","date_gmt":"2020-07-18T15:02:37","guid":{"rendered":"https:\/\/lifeboat.com\/blog\/2020\/07\/automl-zero-evolving-code-that-learns"},"modified":"2020-07-18T08:02:37","modified_gmt":"2020-07-18T15:02:37","slug":"automl-zero-evolving-code-that-learns","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2020\/07\/automl-zero-evolving-code-that-learns","title":{"rendered":"AutoML-Zero: Evolving Code that Learns"},"content":{"rendered":"

<\/a><\/p>\n

The snake bites its tail<\/p>\n

Google AI can independently discover AI methods.<\/p>\n

Then optimizes them<\/p>\n

It Evolves algorithms from scratch\u2014using only basic mathematical operations\u2014rediscovering fundamental ML techniques & showing the potential to discover novel algorithms.<\/p>\n

AutoML-Zero: new research that that can rediscover fundamental ML techniques by searching a space of different ways of combining basic mathematical operations. Arxiv: https:\/\/arxiv.org\/abs\/2003<\/a>.<\/p>\n

\n

Machine learning (ML) has seen tremendous successes recently, which were made possible by ML algorithms like deep neural networks<\/a> that were discovered through years of expert research. The difficulty involved in this research fueled AutoML<\/a><\/em>, a field that aims to automate the design of ML algorithms. So far, AutoML has focused on constructing solutions by combining sophisticated hand-designed components. A typical example is that of neural architecture search<\/a><\/em>, a subfield in which one builds neural networks automatically out of complex layers (e.g., convolutions, batch-norm, and dropout), and the topic<\/a> of much<\/a> research<\/a>.<\/p>\n

Continue reading \u201cAutoML-Zero: Evolving Code that Learns\u201d | ><\/a><\/div><\/p>\n","protected":false},"excerpt":{"rendered":"

The snake bites its tail Google AI can independently discover AI methods. Then optimizes them It Evolves algorithms from scratch\u2014using only basic mathematical operations\u2014rediscovering fundamental ML techniques & showing the potential to discover novel algorithms. AutoML-Zero: new research that that can rediscover fundamental ML techniques by searching a space of different ways of combining basic [\u2026]<\/p>\n","protected":false},"author":556,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[15,41,2229,6],"tags":[],"class_list":["post-110129","post","type-post","status-publish","format-standard","hentry","category-habitats","category-information-science","category-mathematics","category-robotics-ai"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/110129","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/556"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=110129"}],"version-history":[{"count":0,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/110129\/revisions"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=110129"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=110129"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=110129"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}