The Brain & Neural Networks
Online ISSN : 1883-0455
Print ISSN : 1340-766X
ISSN-L : 1340-766X
Search
Advanced search
OR
Browse
Search
Volume 14, Issue 4
Displaying 1-16 of 16 articles from this issue
Show all abstracts
    • |<
    • <
    • 1
    • >
    • >|
  • Modeling Visual Ventral Pathway Based on the Neocognitron
    Takeharu Yoshizuka, Hayaru Shouno, Hiroyuki Miyamoto, Masato Okada, Ku ...
    2007 Volume 14 Issue 4 Pages 266-272
    Published: December 05, 2007
    Released on J-STAGE: November 21, 2008
    DOIhttps://doi.org/10.3902/jnns.14.266
    JOURNAL FREE ACCESS
    Show abstractHide 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.
    View full abstract
    Download PDF (549K)
  • Plane Extraction from Range Data Using Competitive Associative Nets
    Shuichi Kurogi, Takeshi Nishida
    2007 Volume 14 Issue 4 Pages 273-281
    Published: December 05, 2007
    Released on J-STAGE: November 21, 2008
    DOIhttps://doi.org/10.3902/jnns.14.273
    JOURNAL FREE ACCESS
    Show abstractHide abstract
    This paper describes an application of the competitive associative net called CAN2 to plane extraction from range images measured by a laser range scanner (LRS). The CAN2 basically is a neural net for learning efficient piecewise linear approximation of nonlinear functions, and in this application it is utilized for learning piecewise planner (linear) surfaces from the range image. As a result of the learning, the obtained piecewise planner surfaces are more precise than the actual planner surfaces, so that we introduce a method to gather piecewise planner surfaces for reconstructing the actual planner surfaces. We apply this method to the real range image, and examine the effectiveness by means of comparing other methods, such as the USF (University of South Florida) method and a RHT (Randomized Hough Transform) based method.
    View full abstract
    Download PDF (1461K)
    • |<
    • <
    • 1
    • >
    • >|
feedback
 Top