Supervised learning in Hyper-Column Model

Research output: Contribution to conferencePaper

Abstract

In this paper, we propose a supervised learning method in Hyper-Column Model (HCM). HCM is a model to recognize images, and consists of Hierarchical Self-Organizing Maps (HSOM) and Neocognitron (NC). HCM complements disadvantages of HSOM and NC, and inherits advantages from them. There is a problem, however, that HCM does not suit general image recognition in HCM since its learning method is an unsupervised one with competitive learning which is used by Self-Organizing Map (SOM). Therefore, we extended HCM to a supervised learnable model with an associative memory of SOM. We have found that an ability of HCM with supervised learning is superior to the one with unsupervised learning.

Original languageEnglish
Pages481-488
Number of pages8
Publication statusPublished - Dec 1 2005
Event5th Workshop on Self-Organizing Maps, WSOM 2005 - Paris, France
Duration: Sep 5 2005Sep 8 2005

Other

Other5th Workshop on Self-Organizing Maps, WSOM 2005
CountryFrance
CityParis
Period9/5/059/8/05

Fingerprint

Supervised learning
Self organizing maps
Image recognition
Unsupervised learning
Data storage equipment

All Science Journal Classification (ASJC) codes

  • Information Systems

Cite this

Shimada, A., Tsuruta, N., & Taniguchi, R-I. (2005). Supervised learning in Hyper-Column Model. 481-488. Paper presented at 5th Workshop on Self-Organizing Maps, WSOM 2005, Paris, France.

Supervised learning in Hyper-Column Model. / Shimada, Atsushi; Tsuruta, Naoyuki; Taniguchi, Rin-Ichiro.

2005. 481-488 Paper presented at 5th Workshop on Self-Organizing Maps, WSOM 2005, Paris, France.

Research output: Contribution to conferencePaper

Shimada, A, Tsuruta, N & Taniguchi, R-I 2005, 'Supervised learning in Hyper-Column Model', Paper presented at 5th Workshop on Self-Organizing Maps, WSOM 2005, Paris, France, 9/5/05 - 9/8/05 pp. 481-488.
Shimada A, Tsuruta N, Taniguchi R-I. Supervised learning in Hyper-Column Model. 2005. Paper presented at 5th Workshop on Self-Organizing Maps, WSOM 2005, Paris, France.
Shimada, Atsushi ; Tsuruta, Naoyuki ; Taniguchi, Rin-Ichiro. / Supervised learning in Hyper-Column Model. Paper presented at 5th Workshop on Self-Organizing Maps, WSOM 2005, Paris, France.8 p.
@conference{f16caab47bfc4b0da7893f256dac2d0b,
title = "Supervised learning in Hyper-Column Model",
abstract = "In this paper, we propose a supervised learning method in Hyper-Column Model (HCM). HCM is a model to recognize images, and consists of Hierarchical Self-Organizing Maps (HSOM) and Neocognitron (NC). HCM complements disadvantages of HSOM and NC, and inherits advantages from them. There is a problem, however, that HCM does not suit general image recognition in HCM since its learning method is an unsupervised one with competitive learning which is used by Self-Organizing Map (SOM). Therefore, we extended HCM to a supervised learnable model with an associative memory of SOM. We have found that an ability of HCM with supervised learning is superior to the one with unsupervised learning.",
author = "Atsushi Shimada and Naoyuki Tsuruta and Rin-Ichiro Taniguchi",
year = "2005",
month = "12",
day = "1",
language = "English",
pages = "481--488",
note = "5th Workshop on Self-Organizing Maps, WSOM 2005 ; Conference date: 05-09-2005 Through 08-09-2005",

}

TY - CONF

T1 - Supervised learning in Hyper-Column Model

AU - Shimada, Atsushi

AU - Tsuruta, Naoyuki

AU - Taniguchi, Rin-Ichiro

PY - 2005/12/1

Y1 - 2005/12/1

N2 - In this paper, we propose a supervised learning method in Hyper-Column Model (HCM). HCM is a model to recognize images, and consists of Hierarchical Self-Organizing Maps (HSOM) and Neocognitron (NC). HCM complements disadvantages of HSOM and NC, and inherits advantages from them. There is a problem, however, that HCM does not suit general image recognition in HCM since its learning method is an unsupervised one with competitive learning which is used by Self-Organizing Map (SOM). Therefore, we extended HCM to a supervised learnable model with an associative memory of SOM. We have found that an ability of HCM with supervised learning is superior to the one with unsupervised learning.

AB - In this paper, we propose a supervised learning method in Hyper-Column Model (HCM). HCM is a model to recognize images, and consists of Hierarchical Self-Organizing Maps (HSOM) and Neocognitron (NC). HCM complements disadvantages of HSOM and NC, and inherits advantages from them. There is a problem, however, that HCM does not suit general image recognition in HCM since its learning method is an unsupervised one with competitive learning which is used by Self-Organizing Map (SOM). Therefore, we extended HCM to a supervised learnable model with an associative memory of SOM. We have found that an ability of HCM with supervised learning is superior to the one with unsupervised learning.

UR - http://www.scopus.com/inward/record.url?scp=84890267912&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84890267912&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84890267912

SP - 481

EP - 488

ER -