ePrints

Pattern languages: A new paradigm for neurocomputation

Lookup NU author(s): Dr Peter Andras

Downloads

Full text for this publication is not currently held within this repository. Alternative links are provided below where available.

Abstract

Existing neurocomputation models do not describe very faithfully biological neural systems. Here we offer a new look at neural activity data, by introducing the paradigm of pattern languages. Biological examples are presented to provide the biological grounding, and an artificial neural network is described as a simple example of how to interpret neural activity data in terms of pattern languages. The new approach places the emphasis on internal processing within the neural system, instead of the input/output processing, and offers a good balance between the consideration of individual neural activity and of the activity of large numbers of neurons. © 2004 Elsevier B.V. All rights reserved.

Publication metadata

Author(s): Andras P

Publication type: Article

Publication status: Published

Journal: Neurocomputing

Year: 2004

Volume: 58-60

Pages: 223-228

Print publication date: 01/06/2004

ISSN (print): 0925-2312

ISSN (electronic): 1872-8286

Publisher: Elsevier

URL: http://dx.doi.org/10.1016/j.neucom.2004.01.047

DOI: 10.1016/j.neucom.2004.01.047

Altmetrics

Share