{"id":1610,"date":"2019-07-24T13:48:00","date_gmt":"2019-07-24T04:48:00","guid":{"rendered":"http:\/\/cinetjp-static3.nict.go.jp\/english\/?p=1610"},"modified":"2022-08-27T21:31:59","modified_gmt":"2022-08-27T12:31:59","slug":"20190722_4202","status":"publish","type":"event","link":"http:\/\/cinetjp-static3.nict.go.jp\/english\/event\/20190722_4202\/","title":{"rendered":"Wenjun Bai: \u201cPriors for affective representation learning\u201d"},"content":{"rendered":"\n

July 24, 2019
14:00
CiNet 1F Conference Room<\/p>\n\n\n\n

Wenjun Bai, Special Appointed Assistant Professor
Kobe University<\/p>\n\n\n\n

Host:\u00a0Masahiko Haruno<\/a>\u00a0(PI)<\/p>\n\n\n\n

Abstract:
Learning an optimal affective representation is at the root of affective computing. However, the discussion on priors for affective representation learning receives limited research attention. Here, I propose that an optimal affective representation should be continuous and reward orientated. Through deriving a computational model with constraints on early visual learning, I will argue that it is possible to learn continuous affective representations without human-curated labels. One step further, I will share my thoughts on how to implement other biological constraints under the information-theoretic framework, and to recast affective representation learning under the reward based reinforcement learning.<\/p>\n","protected":false},"featured_media":0,"template":"","acf":[],"_links":{"self":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event\/1610"}],"collection":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/event"}],"about":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/types\/event"}],"wp:attachment":[{"href":"http:\/\/cinetjp-static3.nict.go.jp\/english\/wp-json\/wp\/v2\/media?parent=1610"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}