Noisy-OR, Noisy-AND ゲートによる位置不変性の変分学習

• 佐野 崇

  東洋大学

• 一杉 裕志

  産業技術総合研究所

書誌事項

タイトル別名

• Variational Learning of Feature Pooling in a Bayesian Network with Noisy-OR and Noisy-AND Gates

抄録

In the viewpoint of the Bayesian brain hypothesis, Bayesian network model of cerebral cortex is promissing not only for computational modeling of brain, but also for an efficient brain- like artificial intelligence. A norious drawback in a Bayesian network is, however, the number of parameters that grows exponentially against the number of parent variables for a random variable. Restriction of the model may be a solution to this problem. Inspired by the biological plausibility, we previously proposed to use the combination of the noisy-OR and noisy-AND gates, whose numbers of parameters grow linearly with the number of parent random variables. Although we showed that this model can have translation invariance in a small-scale setting, it was difficult to enlarge the scale because of the hidden variables. In this study, we extend the previous attempt by employing a variational learning method to overcome the intractability of the estimation of the massive hidden variables. We can scale the model up to learn the hand-written digit data.

収録刊行物

• 人工知能学会第二種研究会資料

  人工知能学会第二種研究会資料 2020 (AGI-016), 05-, 2020-11-20

  一般社団法人 人工知能学会

詳細情報

• CRID: 1390289398727081728
• NII論文ID: 130008089125
• DOI: 10.11517/jsaisigtwo.2020.agi-016_05
• ISSN: 24365556
• 本文言語コード: ja
• データソース種別:
  • JaLC
  • CiNii Articles
  • KAKEN
• 抄録ライセンスフラグ: 使用可