Please use this identifier to cite or link to this item:
Title: Qualitative computation with neural nets: differential equations like examples
Authors: Delgado, A.
Moreno Díaz, Roberto 
Mira, J.
UNESCO Clasification: 120304 Inteligencia artificial
Issue Date: 1994
Journal: Lecture Notes in Computer Science 
Conference: Eurocast 1993 International Workshop on Computer Aided Systems Theory (EUROCAST 1993) 
Abstract: Linear and non-linear local computation with self-programming facilities is the more used model of biological neural nets. The diversity, specificity and complexity of anatomo-physiological contacts (dendrite-dendrite, axon-axon, axon-dendrite,.) and the variety of local processes carried out by those contacts make one think of authentic subcellular microcomputation. To illustrate the enormous computational capacity asociated to a neuron we present the masks necessary to solve the more usual equations of classical physics (Newton, Diffusion,.) and compare with the dendritic field of a Purkinje cell. Size, form and symmetries in the anatomy of receptive fields are interpreted as responsable of specific spatio-temporal filtering, orientation and movement detection. Furthermore, there is experimental evidence of other algorithmic local functions which do not have an analytical counterpart and consequently are not considered in this paper.
ISBN: 978-3-540-57601-3
ISSN: 0302-9743
DOI: 10.1007/3-540-57601-0_63
Source: Pichler F., Moreno Díaz R. (eds) Computer Aided Systems Theory — . EUROCAST 1993. Lecture Notes in Computer Science, vol 763, pp. 366-379. Springer, Berlin, Heidelberg
Appears in Collections:Actas de congresos
Show full item record


checked on Sep 26, 2021

Page view(s)

checked on Sep 18, 2021

Google ScholarTM




Export metadata

Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.