Presentation 1999/3/19
Self-Learning of the Neocognitron-type Temporal Pattern Recognition Model
Tsukasa AOSHIKA, Sei TAKAHASHI, Yoshifumi SEKINE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we discuss self-learning of the Neocognitron-type Temporal Pattern Recognition Model (Neo-TPRM). Successive learning is introduced into the Neo-TPRM for the adaptive recognition of patterns. For the examination of plasticity of weights, a simplified model is tested by computer simulation. Input patterns having the different number of local features are inputted into the model. The results show that the same number of sets of weights as local features included in the input patterns is formed, and that sets of weights corresponding to local features are vanished if the features are not included in input patterns for a certain period of time.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) neural network / Neocognitron / self-learning / temporal patten
Paper # NC98-156
Date of Issue

Conference Information
Committee NC
Conference Date 1999/3/19(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) Self-Learning of the Neocognitron-type Temporal Pattern Recognition Model
Sub Title (in English)
Keyword(1) neural network
Keyword(2) Neocognitron
Keyword(3) self-learning
Keyword(4) temporal patten
1st Author's Name Tsukasa AOSHIKA
1st Author's Affiliation Department of Electronic Engineering, College of Science & Technology, NIHON UNIVERSITY()
2nd Author's Name Sei TAKAHASHI
2nd Author's Affiliation Department of Electronic Engineering, College of Science & Technology, NIHON UNIVERSITY
3rd Author's Name Yoshifumi SEKINE
3rd Author's Affiliation Department of Electronic Engineering, College of Science & Technology, NIHON UNIVERSITY
Date 1999/3/19
Paper # NC98-156
Volume (vol) vol.98
Number (no) 674
Page pp.pp.-
#Pages 6
Date of Issue