{"id":553,"date":"2014-08-31T20:38:14","date_gmt":"2014-09-01T00:38:14","guid":{"rendered":"http:\/\/sites.hampshire.edu\/ci-lab\/?p=553"},"modified":"2014-08-31T20:38:14","modified_gmt":"2014-09-01T00:38:14","slug":"27-august-2014","status":"publish","type":"post","link":"https:\/\/sites.hampshire.edu\/ci-lab\/2014\/08\/31\/27-august-2014\/","title":{"rendered":"27 August 2014"},"content":{"rendered":"<p>Present: Lee, Tom, Nic, Lance, Mike, Tim, Bill, Kwaku (virtual), Karthik (virtual)<\/p>\n<h2>Tom&#8217;s Benchmarks<\/h2>\n<p>He&#8217;d gladly have help coding and doing experiments on program synthesis benchmark problems.<\/p>\n<h2>Clojush 2<\/h2>\n<p>Clojush 2 is now live. It adds a linear representation for genomes, which is translated into regular Push programs for execution. People should try it out and report bugs!<\/p>\n<h2>Documentation of Recent Push<\/h2>\n<p>Mike (and Nic) will be working on documenting the use of Push as they get to know it.<\/p>\n<h2>Bladder Cancer Data Set<\/h2>\n<p>Clojush 2 has the training error down near 70. Lee hasn&#8217;t figured out how to control overfitting yet.<\/p>\n<h2>Discussion of Paper: Evolving Neural Networks That Are Both Modular and Regular: HyperNeat Plus the Connection Cost Technique Categories and Subject Descriptors<\/h2>\n<ul>\n<li>There are different kinds of modularity, and what we want is different from what they present.<\/li>\n<li>Evolving an interface for functions is hard!\n<ul>\n<li>Push environments might be helpful here.<\/li>\n<\/ul>\n<\/li>\n<li>Varying the &#8220;environment&#8221; of the problem might help.\n<ul>\n<li>Lexicase is sort of like varying the environment. Maybe?<\/li>\n<\/ul>\n<\/li>\n<li>It seems like it would be reasonable to add a test case that tries to improve modularity based on the compressibility of the program.\n<ul>\n<li>We&#8217;d likely be interested in minimizing the amount a program is compressed. Something like: (compressed size of program)\/(uncompressed size of program)<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Present: Lee, Tom, Nic, Lance, Mike, Tim, Bill, Kwaku (virtual), Karthik (virtual) Tom&#8217;s Benchmarks He&#8217;d gladly have help coding and doing experiments on program synthesis benchmark problems. Clojush 2 Clojush 2 is now live. It adds a linear representation for genomes, which is translated into regular Push programs for execution. People should try it out [&hellip;]<\/p>\n","protected":false},"author":635,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-553","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/553"}],"collection":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/users\/635"}],"replies":[{"embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/comments?post=553"}],"version-history":[{"count":1,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/553\/revisions"}],"predecessor-version":[{"id":554,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/553\/revisions\/554"}],"wp:attachment":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/media?parent=553"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/categories?post=553"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/tags?post=553"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}