公开(公告)号：JP2015091359A

公开(公告)日：2015-05-14

申请号：JP2014262673

申请日：2014-12-25

Applicant: ATR ADVANCED TELECOMM RES INST

Inventor： KAWATO MITSUO ,  WATANABE TAKERO ,  SHIBATA KAZUHISA ,  SASAKI YUKA

IPC: A61H1/02 ,  A61M21/00 ,  A63B69/00

Abstract: 【課題】神経活動のデコーディング方法を使用した訓練装置を提供する。【解決手段】訓練装置1000は、被験者の脳内の所定の領域における脳活動を検出するための脳活動検出装置108と、演算処理装置102と、被験者にニューロフィードバック情報(呈示情報)を提示するための出力装置130とを備える。演算処理装置102は、脳神経の活性化のパターンをデコードして、訓練対象となっている事象に対して事前に取得されている目標活性化のパターンに対する近似度を算出し、算出された近似度に基づいて、報酬値を算出し、報酬値に対応する呈示情報を生成する。【選択図】図1

公开(公告)号：EP2777735A4

公开(公告)日：2015-07-01

申请号：EP12846891

申请日：2012-10-31

Applicant: ATR ADVANCED TELECOMM RES INST

Inventor： KAWATO MITSUO ,  WATANABE TAKEO ,  SHIBATA KAZUHISA ,  SASAKI YUKA

IPC: A61M21/00 ,  A61B5/00 ,  A61B5/04 ,  A61B5/0476 ,  A61B5/0482 ,  A61B5/0484 ,  A61B5/055 ,  A61B10/00 ,  A61H1/02 ,  A61M21/02 ,  G01R33/48 ,  G06F3/01

CPC classification number: A61B5/0482 ,  A61B5/0006 ,  A61B5/0042 ,  A61B5/0075 ,  A61B5/04001 ,  A61B5/04008 ,  A61B5/04012 ,  A61B5/0476 ,  A61B5/0484 ,  A61B5/055 ,  A61B5/4064 ,  A61B5/486 ,  A61B5/7246 ,  A61B5/7267 ,  A61B5/742 ,  A61B2505/09 ,  A61B2576/026 ,  A61M21/02 ,  A61M2021/0022 ,  A61M2021/0027 ,  A61M2021/0044 ,  A61M2230/005 ,  A61M2230/10 ,  G01R33/4806 ,  G06F3/015

Abstract: A training apparatus 1000 using a method of decoding nerve activity includes: a brain activity detecting device 108 for detecting brain activity at a prescribed area within a brain of a subject; and an output device 130 for presenting neurofeedback information (presentation information) to the subject. A processing device 102 decodes a pattern of cranial nerve activity, generates a reward value based on a degree of similarity of the decoded pattern with respect to a target activation pattern obtained in advance for the event as the object of training, and generates presentation information corresponding to the reward value.

公开(公告)号：EP1016981A4

公开(公告)日：2005-02-16

申请号：EP99929751

申请日：1999-07-08

Applicant: JAPAN SCIENCE & TECH AGENCY ,  ATR ADVANCED TELECOMM RES INST

Inventor： DOYA KENJI ,  KAWATO MITSUO

IPC: G05B13/02 ,  G05B13/04 ,  G06F15/18 ,  G06N3/00

CPC classification number: G06N99/005 ,  G05B13/0265 ,  G05B13/048

Abstract: A novel highly-adaptable agent learning machine comprises a plurality of learning modules (3) each including a set of an intensive learning system (1) which works on an environment (4) and determines a behavior output for maximizing the reward given as a result of this and an environment predicting system (2) for predicting change of the environment. The smaller the prediction error of the environment predicting system (2) of each learning module (3) is, the larger the responsibility signal is required to have. In proportion to the responsibility signal, the behavior output from the intensive learning system (1) is weighted, and a behavior affecting the environment is given. In an environment having a nonlinearity/unsteadiness, such as a control object or a system, no specific teacher signal is given. The states of various environments and behaviors optimal to the operating modes are switched and combined. Without using foresight knowledge, behavior can be learned flexibly.

公开(公告)号：DE602004032295D1

公开(公告)日：2011-06-01

申请号：DE602004032295

申请日：2004-08-25

Applicant: SONY CORP ,  ATR ADVANCED TELECOMM RES INST

Inventor： ENDO GEN ,  KAWATO MITSUO ,  CHENG GORDON ,  NAKASHINI JUN ,  MORIMOTO JUN

IPC: B25J5/00 ,  B62D57/032 ,  B25J9/16 ,  B25J13/08