Modeling Visual Ventral Pathway Based on the Neocognitron

• Yoshizuka Takeharu

  Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology

• Shouno Hayaru

  Graduate School of Medicine, Yamaguchi University

• Miyamoto Hiroyuki

  Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology

• Okada Masato

  Graduate School of Frontier Sciences, The University of Tokyo

• Fukushima Kunihiko

  Graduate School of Informatics, Kansai University

Bibliographic Information

Other Title

• ネオコグニトロンによる視覚腹側経路のモデル化

Abstract

It is known that the object recognition is processed in the ventral pathway of the visual system in humans and monkeys. The neocognitron that was proposed by Fukushima is a hierarchical neural network model for pattern recognition. In this paper, we show that the neocognitron can be regarded as a proper biological model of the ventral pathway. From the biological point of view, the model of the ventral pathway should satisfy the following conditions. The model should be hierarchical, the synaptic connections should spread locally, and each component in the hierarchy should be homogeneous. The network architecture of the neocognitron satisfies these conditions. Thus, we investigate the functional similarity between the neocognitron and the ventral pathway. We compared the response property of the neocognitron with that of IT cells. On comparing our results with those obtained by Logothetis et al., we found that the result were very similar qualitatively. Thus, we conclude that the neocognitron is a proper model for the ventral pathway.

Journal

• The Brain & Neural Networks

  The Brain & Neural Networks 14 (4), 266-272, 2007

  Japanese Neural Network Society

Details

• CRID: 1390282679443568384
• NII Article ID: 10020018963
• NII Book ID: AA11658570
• DOI: 10.3902/jnns.14.266
• ISSN: 18830455
• ISSN: 1340766X
• Text Lang: ja
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed