Receptive field atlas and related CNN models

V. Gál, J. Hámori, T. Roska, D. Bálya, Z. S. Borostyánkoi, M. Brendel, K. Lotz, L. Négyessy, L. Orzó, I. Petrás, C. S. Rekeczky, J. Takács, P. Venetiáner, Z. Vidnyánszky, A. Zarándy

Research output: Contribution to journalArticle

11 Citations (Scopus)

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 flexibility of the CNN computing: visual, tactile and auditory modalities are concerned.

Original languageEnglish
Pages (from-to)551-584
Number of pages34
JournalInternational Journal of Bifurcation and Chaos in Applied Sciences and Engineering
Volume14
Issue number2
DOIs
Publication statusPublished - Feb 2004

Fingerprint

Receptive Field
Atlas
Paradigm
Neural Networks
Neural networks
Model
Computer architecture
Neurology
Computer Architecture
Synapse
Signal processing
Interconnection
Modality
Signal Processing
Feedback
Engineers
Flexibility
Logic
Analogue
Processing

Keywords

  • Cellular neural networks
  • Cellular nonlinear networks
  • CNN
  • Feedback network layers
  • Feedforward
  • Local interconnections
  • Receptive field calculus
  • Receptive fields
  • Visual, auditory and tactile system modeling

ASJC Scopus subject areas

  • General
  • Applied Mathematics

Cite this

Receptive field atlas and related CNN models. / Gál, V.; Hámori, J.; Roska, T.; Bálya, D.; Borostyánkoi, Z. S.; Brendel, M.; Lotz, K.; Négyessy, L.; Orzó, L.; Petrás, I.; Rekeczky, C. S.; Takács, J.; Venetiáner, P.; Vidnyánszky, Z.; Zarándy, A.

In: International Journal of Bifurcation and Chaos in Applied Sciences and Engineering, Vol. 14, No. 2, 02.2004, p. 551-584.

Research output: Contribution to journalArticle

Gál, V. ; Hámori, J. ; Roska, T. ; Bálya, D. ; Borostyánkoi, Z. S. ; Brendel, M. ; Lotz, K. ; Négyessy, L. ; Orzó, L. ; Petrás, I. ; Rekeczky, C. S. ; Takács, J. ; Venetiáner, P. ; Vidnyánszky, Z. ; Zarándy, A. / Receptive field atlas and related CNN models. In: International Journal of Bifurcation and Chaos in Applied Sciences and Engineering. 2004 ; Vol. 14, No. 2. pp. 551-584.
@article{c6c040e0c7634943aff3c4f3f7268e0c,
title = "Receptive field atlas and related CNN models",
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 flexibility of the CNN computing: visual, tactile and auditory modalities are concerned.",
keywords = "Cellular neural networks, Cellular nonlinear networks, CNN, Feedback network layers, Feedforward, Local interconnections, Receptive field calculus, Receptive fields, Visual, auditory and tactile system modeling",
author = "V. G{\'a}l and J. H{\'a}mori and T. Roska and D. B{\'a}lya and Borosty{\'a}nkoi, {Z. S.} and M. Brendel and K. Lotz and L. N{\'e}gyessy and L. Orz{\'o} and I. Petr{\'a}s and Rekeczky, {C. S.} and J. Tak{\'a}cs and P. Veneti{\'a}ner and Z. Vidny{\'a}nszky and A. Zar{\'a}ndy",
year = "2004",
month = "2",
doi = "10.1142/S0218127404009545",
language = "English",
volume = "14",
pages = "551--584",
journal = "International Journal of Bifurcation and Chaos in Applied Sciences and Engineering",
issn = "0218-1274",
publisher = "World Scientific Publishing Co. Pte Ltd",
number = "2",

}

TY - JOUR

T1 - Receptive field atlas and related CNN models

AU - Gál, V.

AU - Hámori, J.

AU - Roska, T.

AU - Bálya, D.

AU - Borostyánkoi, Z. S.

AU - Brendel, M.

AU - Lotz, K.

AU - Négyessy, L.

AU - Orzó, L.

AU - Petrás, I.

AU - Rekeczky, C. S.

AU - Takács, J.

AU - Venetiáner, P.

AU - Vidnyánszky, Z.

AU - Zarándy, A.

PY - 2004/2

Y1 - 2004/2

N2 - 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 flexibility of the CNN computing: visual, tactile and auditory modalities are concerned.

AB - 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 flexibility of the CNN computing: visual, tactile and auditory modalities are concerned.

KW - Cellular neural networks

KW - Cellular nonlinear networks

KW - CNN

KW - Feedback network layers

KW - Feedforward

KW - Local interconnections

KW - Receptive field calculus

KW - Receptive fields

KW - Visual, auditory and tactile system modeling

UR - http://www.scopus.com/inward/record.url?scp=13844255205&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13844255205&partnerID=8YFLogxK

U2 - 10.1142/S0218127404009545

DO - 10.1142/S0218127404009545

M3 - Article

VL - 14

SP - 551

EP - 584

JO - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

JF - International Journal of Bifurcation and Chaos in Applied Sciences and Engineering

SN - 0218-1274

IS - 2

ER -