Receptive field atlas and related CNN models

Gál, Viktor and Hámori, J. and Roska, Tamás and Bálya, Dávid and Borostyánkői, ZS and Brendel, M. and Lotz, K. and Négyessy, L. and Orzó, László and Petrás, István and Rekeczky, Csaba and Takács, J. and Venetiáner, P. and Vidnyánszky, Z. and Zarándy, Ákos (2004) Receptive field atlas and related CNN models. INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 14 (2). pp. 551-584. ISSN 0218-1274

[img]
Preview
Text
gal2004receptive.pdf - Submitted Version

Download (2MB) | Preview

Abstract

In this paper we demonstrate the potential of the cellular nonlinear/neural network paradigm (CNN) that of the analogic cellular computer architecture (called CNN Universal Machine | CNN-UM) in modeling different parts and aspects of the nervous system. The structure of the living sensory systems and the CNN share a lot of features in common: local interconnections ("receptive field architecture"), nonlinear and delayed synapses for the processing tasks, the potentiality of feedback and using the advantages of both the analog and logic signal-processing mode. The results of more than ten years of cooperative work of many engineers and neurobiologists have been collected in an atlas: what we present here is a kind of selection from these studies emphasizing the exibility of the CNN computing: visual, tactile and auditory modalities are concerned.

Item Type: ISI Article
Subjects: Q Science > QA Mathematics and Computer Science > QA75 Electronic computers. Computer science / számítástechnika, számítógéptudomány
Divisions: Cellular Sensory and Optical Wave Computing Laboratory
Depositing User: Eszter Nagy
Date Deposited: 11 Dec 2012 15:17
Last Modified: 18 Mar 2013 11:39
URI: http://eprints.sztaki.hu/id/eprint/3733

Update Item Update Item