{"id":123,"date":"2005-09-20T17:18:17","date_gmt":"2005-09-20T23:18:17","guid":{"rendered":"http:\/\/hunch.net\/?p=123"},"modified":"2005-09-20T17:18:39","modified_gmt":"2005-09-20T23:18:39","slug":"workshop-proposal-atomic-learning","status":"publish","type":"post","link":"https:\/\/hunch.net\/?p=123","title":{"rendered":"Workshop Proposal: Atomic Learning"},"content":{"rendered":"

This is a proposal for a workshop. It may or may not happen depending on the level of interest. If you are interested, feel free to indicate so (by email or comments).<\/p>\n

Description:
\nAssume(*) that any system for solving large difficult learning problems must decompose into repeated use of basic elements (i.e. atoms). There are many basic questions which remain:<\/p>\n

    \n
  1. What are the viable basic elements?<\/li>\n
  2. What makes a basic element viable?<\/li>\n
  3. What are the viable principles for the composition of these basic elements?<\/li>\n
  4. What are the viable principles for learning in such systems?<\/li>\n
  5. What problems can this approach handle?<\/li>\n<\/ol>\n

    Hal Daume adds:<\/p>\n

      \n
    1. Can composition of atoms be (semi-) automatically constructed[?]<\/li>\n
    2. When atoms are constructed through reductions, is there some notion of the “naturalness” of the created leaning problems?<\/li>\n
    3. Other than Markov fields\/graphical models\/Bayes nets, is there a good language for representing atoms and their compositions?<\/li>\n<\/ol>\n

      The answer to these and related questions remain unclear to me. A workshop gives us a chance to pool what we have learned from some very different approaches to tackling this same basic goal.<\/p>\n

      (*) As a general principle, it’s very difficult to conceive of any system for solving any large problem which does not decompose.<\/p>\n

      Plan Sketch:<\/p>\n

        \n
      1. A two day workshop with unhurried presentations and discussion seems appropriate, especially given the diversity of approaches.<\/li>\n
      2. TTI-Chicago may be able to help with costs.<\/li>\n<\/ol>\n

        The above two points suggest having a workshop on a {Friday, Saturday} or {Saturday, Sunday} at TTI-Chicago.<\/p>\n","protected":false},"excerpt":{"rendered":"

        This is a proposal for a workshop. It may or may not happen depending on the level of interest. If you are interested, feel free to indicate so (by email or comments). Description: Assume(*) that any system for solving large difficult learning problems must decompose into repeated use of basic elements (i.e. atoms). There are … <\/p>\n

        Continue reading “Workshop Proposal: Atomic Learning”<\/span><\/a><\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-123","post","type-post","status-publish","format-standard","hentry","category-general"],"_links":{"self":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/123","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=123"}],"version-history":[{"count":0,"href":"https:\/\/hunch.net\/index.php?rest_route=\/wp\/v2\/posts\/123\/revisions"}],"wp:attachment":[{"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=123"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=123"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hunch.net\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=123"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}