Akira Date

J-GLOBAL         Last updated: Jan 23, 2019 at 19:20
 
Avatar
Name
Akira Date
Affiliation
University of Miyazaki
Section
Faculty of Engineering

Research Areas

 
 

Academic & Professional Experience

 
Apr 2007
 - 
Today
Associate Professor, University of Miyazaki
 
Dec 2004
 - 
Mar 2007
Associate Professor, University of Miyazaki
 
Apr 2002
 - 
Mar 2004
Researcher, Communication Research Laboratory
 
May 1999
 - 
Mar 2002
Staff Scientist, RIKEN Brain Science Institute
 
Oct 1996
 - 
May 1999
visiting scholar, Division of Applied Mathematics, Brown University
 

Education

 
Apr 1987
 - 
Mar 1991
Department of Communication and Systems Engineering, University of Electro-Communications
 

Published Papers

 
A Self-Organization Model Developing Higher Order Units by Self-Test Learning
Akira Date, Shunsuke Hanai
IEICE Technical Report   118(284) 419-424   Nov 2018
MIYATA Ryota, DATE Akira, KURATA Koji
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics   23(2) 243-253   Apr 2011   [Refereed]
There have been many studies about dynamics of neural fields. Especially, the neural field which allowed localized excitation areas provided base for the self-organizing map (SOM) algorithm. Here, we focus on a neural oscillatory field, and propos...
Akira Date
Artificial Life and Robotics   13 517-521   2009   [Refereed]
Akira Date, Koji Kurata
12 291-294   2008   [Refereed]
DATE Akira, KURATA Koji
The transactions of the Institute of Electronics, Information and Communication Engineers. D-II   88(2) 211-217   Feb 2005   [Refereed]
物体の向き, 位置, 大きさなどによらない不変な認識が脳内でどのように実現されているかは不明な点が多い.大脳の視覚一次野(V1)には, 網膜に投影された像のある程度の大きさの領域内であればどの場所に線分が提示されても反応する複雑型細胞と呼ばれる細胞があり, 物体の見え方に不変な認識に重要な役割を担っていると考えられている.この複雑型細胞がもつ性質は, 神経活動の時間的持続性を利用したヘブ学習(トレース学習)により説明されてきた.本論文では, 従来のモデルで示された結果と同等な性質を, トレ...
DATE Akira
The transactions of the Institute of Electronics, Information and Communication Engineers. D-II   87(8) 1697-1706   Aug 2004   [Refereed]
眼に映る画像を局所的に見るとその解釈はあいまいであるが,画像全体としての解釈があいまいであることはない.これは外界のモデルを人間が学習により獲得しており,それをもとに,もっともらしい解釈づけを行っているからである.これは,脳内の視覚情報処理において,視覚入力から前向きのみならず逆向性の信号が重要な役割を果たしていると考えられている理由でもある.本論文では,あいまい性を保ちながら前向き処理を進め,逆向きの処理であいまい性を解消するモデルを提案する.モデルとして,階層的な知識構造を表現できる木...
DATE Akira, KURATA Koji
The transactions of the Institute of Electronics, Information and Communication Engineers. D-II   87(7) 1529-1538   Jul 2004   [Refereed]
部屋の中を自由に動くロボットからの視覚時系列信号から,ロボットの位置と向きの情報を分離して抽出する神経回路モデルを提案する.本モデルは2次元の神経場(素子面)を環状に並べた3次元構造をもち,学習アルゴリズムは,各素子面内ではニューラルガス,環状方向には自己組織マップ(SOM)の性質をもつ.計算機シミュレーションにより,視覚入力からロボットの位置と向きの情報を抽出できることを示し,学習アルゴリズムの有効性を確認した.
On the number of equilibrium states in weakly coupled random networks
Akira Date, Chii-Ruey Hwang and Shuenn-Jyi Sheu
Statistics & Probability Letters   49 291-297   2000   [Refereed]
A statistical technique for the detection of fine temporal structure in multi-neuronal spike trains
Akira Date, Elie Bienenstock and Stuart Geman
Society for Neuroscience Abstracts   25(2) 1411   1999
On the temporal resolution of neural activity
Akira Date, Elie Bienenstock and Stuart Geman
Technical Report, Division of Applied Mathematics, Brown University, Providence, RI      May 1998
Date Akira
Transactions of the Japan Society for Industrial and Applied Mathematics   7(2) 97-106   Jun 1997   [Refereed]
A large number of equilibrium states or fixed points is in a randomly and symmetrically connected neural network. Recently it has been shown that the maximum number which can be realized depend on the model of the single neuron. Here we show some ...
Date Akira, Kurata Koji, Amari Shun-ichi
Transactions of the Japan Society for Industrial and Applied Mathematics   6(1) 15-28   Mar 1996   [Refereed]
A class of recurrent neural networks is considered in which w_<ij>the connection weight from the jth to the ith element, is randomly generated under the condition wij=wji. The expected number of equilibrium states in the network consisting of two-...
Configurational encoding of complex visual forms by single neurons of monkey temporal cortex
Yasushi Miyashita, Akira Date and Hiroyuki Okuno
Neuropsychologia   31 1119-1131   1993   [Refereed]

Misc

 
DATE Akira
IEICE technical report. Neurocomputing   109(461) 285-290   Mar 2010
Probabilistic generative models work in many applications of image analysis and speech recognition. In general, there is an observation vector y and a state vector x, and a joint dependency structure among them. The object of interest is, given y,...
伊達 章, 窪田 光, 山田 雄輔
電子情報通信学会技術研究報告 = IEICE technical report : 信学技報   116(259) 19-24   Oct 2016
DATE Akira, KURATA Koji
IEICE technical report. Neurocomputing   112(480) 203-208   Mar 2013
We propose a learning algorithm for Boltzmann neural fields [1] developed by Kurata (1988). The Boltzmann machine learning algorithm is theoretically elegant and easy to implement in hardware but very slow in networks with interconnected hidden un...
DATE Akira
IEICE technical report. Neurocomputing   105(130) 43-48   Jun 2005
For university students, if learning dynamics of neural network models is shown graphically in computer simulation, it accelerates the understanding of the behavior of the models. I have made the software for this purpose. Here I exemplify the cod...
DATE Akira, YAMAMOTO Hiroshi
IEICE technical report. Neurocomputing   108(480) 399-404   Mar 2009
In 2008, Professor Hopfield proposed a network model of associative memory which can rapidly detect the failure of memory recalls. The model consists of neurons with piecewise linear activity function, and stores struc-tured sparsely-encoded activ...

Conference Activities & Talks

 
Experiments of a self-organization machine discovering regularities in high-dimensional environment
Akira Date, Shunsuke Hanai
Champalimaud Research Symposium, Quantitative approaches to Behaviour and Neural Systems   25 Oct 2018   

Research Grants & Projects

 
Ministry of Education, Culture, Sports, Science and Technology: Grants-in-Aid for Scientific Research(基盤研究(C))
Project Year: 2007 - 2009    Investigator(s): Akira DATE
The area of hippocampus in the brain is involved in associative memory recall in which new neurons are born every day. To study the meaning of new-born neurons, we analyzed a property of associative memory networks in which a number of units are r...