Committee |
Date Time |
Place |
Paper Title / Authors |
Abstract |
Paper # |
NC, NLP (Joint) |
2016-01-29 15:50 |
Fukuoka |
Kyushu Institute of Technology |
Node-perturbation Learning for Soft-committee machine Kazuyuki Hara (Nihon Univ.), Kentaro Katahira (Nagoya Univ.) NC2015-66 |
Node perturbation learning is a stochastic gradient descent method for neural networks. It estimates the gradient of the... [more] |
NC2015-66 pp.49-54 |
NC, MBE (Joint) |
2013-07-19 14:30 |
Tokushima |
The University of Tokushima |
Statistical Mechanics of node-perturbation Learning using two independent noises Kazuyuki Hara (Nihon Univ.), Kentaro Katahira, Masato Okada (Univ. of Tokyo) NC2013-17 |
Node perturbation learning is a stochastic gradient descent method for neural networks. It estimates the gradient by com... [more] |
NC2013-17 pp.13-18 |
NC |
2012-01-26 14:25 |
Hokkaido |
Future University Hakodate |
A recurrent network for multisensory integration
-- Identification of common sources of audiovisual stimuli -- Itsuki Yamashita (Tokyo Univ.), Kentaro Katahira (JST), Yasuhiko Igarashi (Tokyo Univ.), Kazuo Okanoya (JST), Masato Okada (Tokyo Univ.) NC2011-105 |
We percept surrounding environments using several organs of sense. How we estimate surrounding information from multisen... [more] |
NC2011-105 pp.47-52 |
NC |
2011-10-20 13:10 |
Fukuoka |
Ohashi Campus, Kyushu Univ. |
Statistical Mechanics of Node-Perturbation Learning for Nonlinear Perceptron Kazuyuki Hara (Nihon Univ.), Kentaro Katahira (JST), Kazuo Okanoya (RIKEN), Masato Okada (Tokyo Univ.) NC2011-63 |
Node-perturbation learning is a kind of statistical gradient descent algorithm that can be applied to problems where the... [more] |
NC2011-63 pp.107-112 |
NC |
2011-07-26 15:55 |
Hyogo |
Graduate School of Engineering, Kobe University |
Bayesian decision making model accounts for matching behavior Hiroshi Saito (Univ. of Tokyo), Kentaro Katahira (Univ. of Tokyo/RIKEN/JST-ERATO), Kazuo Okanoya (RIKEN/JST), Masato Okada (Univ. of Tokyo/RIKEN/JST) NC2011-44 |
It is an important issue whether decision making processes in human and animal brains are deterministic or probabilistic... [more] |
NC2011-44 pp.129-134 |
NC, MBE (Joint) |
2011-03-09 10:40 |
Tokyo |
Tamagawa University |
Synaptic learning rule that can explain exponential history dependency of decision making on reward history during matching behavior Hiroshi Saito (Univ. of Tokyo), Kentaro Katahira (Univ. of Tokyo/RIKEN/JST-ERATO), Kazuo Okanoya (RIKEN/JST), Masato Okada (Univ. of Tokyo/RIKEN/JST) NC2010-184 |
[more] |
NC2010-184 pp.337-341 |
NC, NLP |
2009-07-14 13:00 |
Nara |
NAIST |
Statistical Mechanics of Node-perturbation learning Kazuyuki Hara (Tokyo Metro. Colle. Ind. Eng.), Kentaro Katahira (ERATO), Kazuo Okanoya (RIKEN), Masato Okada (Tokyo Univ.) NLP2009-38 NC2009-31 |
Node-perturbation learning is a stochastic gradient method, and it can
apply to the problem where the objective functi... [more] |
NLP2009-38 NC2009-31 pp.127-132 |
NC |
2009-01-19 14:45 |
Hokkaido |
Hokkaido Univ. |
Node perturbation learning with noisy reference Tatsuya Cho (Univ. of Tokyo), Kentaro Katahira, Masato Okada (Univ of Tokyo/RIKEN Brain Scie Inst.) NC2008-89 |
We propose a node perturbation learning with noisy reference signal. Recently, the method for node
perturbation has inv... [more] |
NC2008-89 pp.43-47 |
NC |
2009-01-20 14:40 |
Hokkaido |
Hokkaido Univ. |
Which model can properly describe dynamics and smoothness of firing rate? Ken Takiyama (The Univ. of Tokyo), Kentaro Katahira, Masato Okada (The Univ. of Tokyo/RIKEN) NC2008-98 |
We construct the algorithm using belief propagation(BP), which algorithm simultaneously estimates
firing rate and calcu... [more] |
NC2008-98 pp.89-94 |
NC |
2007-10-18 09:55 |
Miyagi |
Tohoku University |
Variational Bayes Hidden Markov Models for extracting spatiotemporal spike pattern Kentaro Katahira (Univ. Tokyo/RIKEN), Jun Nishikawa, Kazuo Okanoya (RIKEN), Masato Okada (Univ. Tokyo/RIKEN) NC2007-34 |
Hidden Markov Model (HMM) is used to extracting spatio-temporal pattern from spikes recorded by
multielectrode. The EM ... [more] |
NC2007-34 pp.7-12 |
NC |
2007-03-15 15:30 |
Tokyo |
Tamagawa University |
Deterministic Annealing in Variational Baysian Algorithm Kentaro Katahira (Univ. Tokyo/RIKEN), Kazuho Watanabe (Tokyo Tech), Masato Okada (Univ. Tokyo/RIKEN) |
Variational Bayes (VB) algorithm is widely used as an approximation of Bayesian method. The VB algorithm can approximate... [more] |
NC2006-183 pp.177-182 |
NC |
2007-01-26 10:10 |
Hokkaido |
Noboribetsu Manseikaku(Noboribetsu) |
Retrieval process of branching sequences in associative memory with common input Kentaro Katahira (Univ. Tokyo), Masaki Kawamura (Yamaguchi Univ.), Kazuo Okanoya (RIKEN), Masato Okada (Univ. Tokyo) |
Retrieval of memory sequences is one of the important functions in the brain. There have been much of studies about neur... [more] |
NC2006-102 pp.11-16 |
NC |
2006-07-14 14:55 |
Tokyo |
Waseda University |
A neural circuit model for generating complex birdsong syntax Kentaro Katahira (Univ. of Tokyo), Kazuo Okanoya (RIKEN), Masato Okada (Univ. of Tokyo) |
Abstract The singing behavior of songbirds has been investigated as a model of sequence learning and production. The son... [more] |
NC2006-42 pp.25-30 |