Presentation 2012-07-31
A Biological Implementation of Bayesian Estimation Algorithm in a Neural Network Architecture Based on Discrete Choice Theory
Daiki FUTAGI, Ryota KOBAYASHI, Katsunori KITANO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Bayesian estimation theory has been expected to explain how brain deals with uncertainty such as feature extraction against noisy observations. It has been implied that the neural networks that model cortical network could implement the Bayesian estimation algorithm by several previous studies. However, it is still unclear whether it is possible to implement the required computational procedures of the algorithm under physiological and anatomical constraints of the neural systems. We here propose the neural network that implements the algorithm in a biologically plausible manner, incorporating the discrete choice theory into the previously proposed model. Our model successfully demonstrated an orientation discrimination task with significantly noisy visual images.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Bayesian estimation theory / neural network / discrete choice theory / normalization / log-normal distribution
Paper # NC2012-28
Date of Issue

Conference Information
Committee NC
Conference Date 2012/7/23(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Biological Implementation of Bayesian Estimation Algorithm in a Neural Network Architecture Based on Discrete Choice Theory
Sub Title (in English)
Keyword(1) Bayesian estimation theory
Keyword(2) neural network
Keyword(3) discrete choice theory
Keyword(4) normalization
Keyword(5) log-normal distribution
1st Author's Name Daiki FUTAGI
1st Author's Affiliation Graduate School of Information Science and Engineering, Ritsumeikan University()
2nd Author's Name Ryota KOBAYASHI
2nd Author's Affiliation Department of Information Science and Engineering, Ritsumeikan University
3rd Author's Name Katsunori KITANO
3rd Author's Affiliation Department of Information Science and Engineering, Ritsumeikan University
Date 2012-07-31
Paper # NC2012-28
Volume (vol) vol.112
Number (no) 168
Page pp.pp.-
#Pages 6
Date of Issue