{"id":390,"date":"2013-10-10T11:35:39","date_gmt":"2013-10-10T15:35:39","guid":{"rendered":"http:\/\/sites.hampshire.edu\/ci-lab\/?p=390"},"modified":"2013-10-10T11:35:40","modified_gmt":"2013-10-10T15:35:40","slug":"9-october-2013","status":"publish","type":"post","link":"https:\/\/sites.hampshire.edu\/ci-lab\/2013\/10\/10\/9-october-2013\/","title":{"rendered":"9 October 2013"},"content":{"rendered":"<p>Present: Lee, Tom (scribe), Bill, Daniel, Jake, Karthik, Eddie, Frode, George, Omri<\/p>\n<p>No meeting next week. The following week, Conor and Chris will be visiting our meeting, and will also talk from 4:00-5:30 that day.<\/p>\n<h1>Updates<\/h1>\n<h2>Jake<\/h2>\n<ul>\n<li>Working on Push visualization.<\/li>\n<li>Div 3: Growth + Animation<\/li>\n<\/ul>\n<h2>Omri<\/h2>\n<ul>\n<li>SIMD and complexity theory<\/li>\n<li>Integer sequences and GP<\/li>\n<li>Evolving test cases?<\/li>\n<\/ul>\n<h2>Eddie<\/h2>\n<ul>\n<li>Working on Python Push<\/li>\n<\/ul>\n<h2>Frode<\/h2>\n<ul>\n<li>Reading about other evolutionary algorithms.<\/li>\n<\/ul>\n<h2>Bill<\/h2>\n<ul>\n<li>Switching back to a developmental approach<\/li>\n<\/ul>\n<h2>Daniel<\/h2>\n<ul>\n<li>Div 3: GP + mathematics<\/li>\n<li>When will GP solve a problem<\/li>\n<\/ul>\n<h1>Topics<\/h1>\n<h2>Israel Trip<\/h2>\n<ul>\n<li>Someone should look into Humies awards to see what makes good GP results.<\/li>\n<\/ul>\n<h2>Max-Points Bug<\/h2>\n<ul>\n<li>\u00a0Because the pushgp argument (max-points) has a different name from the global variable (global-max-points-in-program), the global variable is not being reset when max-points is given as an argument\n<ul>\n<li>This is a problem for Push instructions that use the global variable to determine if a piece of code is too big to put on the code\/exec stacks. In particular, many code stack instructions and exec_s and exec_y use it to limit the size of code on those stacks. Because of this bug, those instructions will limit code to 100 points during execution, even if max-points is set by a pushgp argument.<\/li>\n<li>Fortunately, this bug <span style=\"text-decoration: underline\">does not<\/span> affect genetic operators, which use max-points directly when it is passed to the breed function.<\/li>\n<\/ul>\n<\/li>\n<li>Tom is going to fix this bug by changing all occurrences of &#8220;global-max-points-in-program&#8221; to &#8220;global-max-points&#8221;. He will also check if there are any other name mismatches between global variables and pushgp arguments.<\/li>\n<\/ul>\n<h2>\u00a0No-Paren Mutation ULTRA<\/h2>\n<ul>\n<li>An initial look into no-paren mutation ULTRA looks good using the Change problem.<\/li>\n<li>But, since the Change problem doesn&#8217;t use semantic parens, we should test it on a problem that requires paren structure.<\/li>\n<li>Tom will test it on a synthetic problem that we discussed, which we will, for now, call the &#8220;damped oscillator tree&#8221; problem, which builds a program that looks like this:\n<ul>\n<li>(0 0 0 0 0 ((0 0 0 ((0) 0 0)) 0 0 0 0))<\/li>\n<li>The problem will (initially) use overlap as the fitness function.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<h2>Calc Problem<\/h2>\n<ul>\n<li>Alternative error measures like Levenshtein distance could be important.<\/li>\n<li>Which test cases should we use out of all of them?\n<ul>\n<li>For now, we want to try using a random subset of all the test cases each generation.<\/li>\n<li>This will require validation of seemingly perfect solutions. It may be possible to do this in the problem-specific report.<\/li>\n<li>Tom notes that Schmidt and Lipson tried random subsets of test cases in their co-evolved fitness predictors work, and they fared rather poorly.<\/li>\n<li>If this works for Calc, we should also try it for WC.<\/li>\n<\/ul>\n<\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Present: Lee, Tom (scribe), Bill, Daniel, Jake, Karthik, Eddie, Frode, George, Omri No meeting next week. The following week, Conor and Chris will be visiting our meeting, and will also talk from 4:00-5:30 that day. Updates Jake Working on Push visualization. Div 3: Growth + Animation Omri SIMD and complexity theory Integer sequences and GP [&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-390","post","type-post","status-publish","format-standard","hentry","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/390"}],"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=390"}],"version-history":[{"count":3,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/390\/revisions"}],"predecessor-version":[{"id":393,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/posts\/390\/revisions\/393"}],"wp:attachment":[{"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/media?parent=390"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/categories?post=390"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/sites.hampshire.edu\/ci-lab\/wp-json\/wp\/v2\/tags?post=390"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}