{"id":810817,"date":"2022-01-10T16:53:01","date_gmt":"2022-01-11T00:53:01","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&#038;p=810817"},"modified":"2022-01-11T14:31:01","modified_gmt":"2022-01-11T22:31:01","slug":"chunking-tprs","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/chunking-tprs\/","title":{"rendered":"TPR Chunking"},"content":{"rendered":"<section class=\"mb-3 moray-highlight\">\n\t<div class=\"card-img-overlay mx-lg-0\">\n\t\t<div class=\"card-background bg-gray-200 has-background- card-background--full-bleed\">\n\t\t\t\t\t<\/div>\n\t\t<!-- Foreground -->\n\t\t<div class=\"card-foreground d-flex mt-md-n5 my-lg-5 px-g px-lg-0\">\n\t\t\t<!-- Container -->\n\t\t\t<div class=\"container d-flex mt-md-n5 my-lg-5 align-self-center\">\n\t\t\t\t<!-- Card wrapper -->\n\t\t\t\t<div class=\"w-100 w-lg-col-5\">\n\t\t\t\t\t<!-- Card -->\n\t\t\t\t\t<div class=\"card material-md-card py-5 px-md-5\">\n\t\t\t\t\t\t<div class=\"card-body \">\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n<h1 id=\"tpr-chunking\">TPR Chunking<\/h1>\n\n\n\n<p>Neural Networks processing information as chunks of structured items, encoded into Tensor Product Representations.<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n<p> The theory of chunking developed out of George Miller&#8217;s study of <a class=\"msr-external-link glyph-append glyph-append-open-in-new-tab glyph-append-xsmall\" href=\"http:\/\/www2.psych.utoronto.ca\/users\/peterson\/psy430s2001\/Miller%20GA%20Magical%20Seven%20Psych%20Review%201955.pdf\">working memory in humans<span class=\"sr-only\"> (opens in new tab)<\/span><\/a>.&nbsp; It can be used to explain how humans can effectively exceed the capacity of their working memory (7 plus or minus 2 items) by organizing (recoding) the items into a number of groups (chunks).&nbsp; This project explores whether Neural Networks can process relatively large structures of items using a chunking approach, where each chunk of items is a small structure encoded into a Tensor Product Representation (TPR).<\/p>\n\n\n","protected":false},"excerpt":{"rendered":"<p>Neural Networks processing information as chunks of structured items, encoded into Tensor Product Representations. The theory of chunking developed out of George Miller&#8217;s study of working memory in humans (opens in new tab).&nbsp; It can be used to explain how humans can effectively exceed the capacity of their working memory (7 plus or minus 2 [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"research-area":[13556],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-810817","msr-project","type-msr-project","status-publish","hentry","msr-research-area-artificial-intelligence","msr-locale-en_us","msr-archive-status-active"],"msr_project_start":"2022-01-11","related-publications":[],"related-downloads":[],"related-videos":[],"related-groups":[],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"slides":[],"related-researchers":[{"type":"user_nicename","display_name":"Paul Smolensky","user_id":36353,"people_section":"People Section","alias":"psmo"},{"type":"user_nicename","display_name":"Roland Fernandez","user_id":33386,"people_section":"People Section","alias":"rfernand"},{"type":"user_nicename","display_name":"Jianfeng Gao","user_id":32246,"people_section":"People Section","alias":"jfgao"}],"msr_research_lab":[],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/810817"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":3,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/810817\/revisions"}],"predecessor-version":[{"id":811045,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/810817\/revisions\/811045"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=810817"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=810817"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=810817"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=810817"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=810817"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}