Share Email Print

Proceedings Paper

Transformations of neural inputs in lattice dendrite computation
Author(s): Gonzalo Urcid
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In the present paper, lattice dendrite computation is extended with non-linear transformations of neural inputs that are applied before local discrimination is performed by each dendrite of an artificial neuron. At the expense of increasing the gap with biological analogies or biophysical similarities, the proposed mathematical extension to the basic single layer lattice perceptron model has the advantage that with appropriate input transformations one type synaptic connections can be used, excitatory or inhibitory only; similarly, a reduction in the number of dendrites needed to solve certain one-class recognition problems can be achieved. Illustrative examples are given to show the new capabilities and possible applications of this enhanced single layer lattice perceptron.

Paper Details

Date Published: 30 August 2005
PDF: 12 pages
Proc. SPIE 5916, Mathematical Methods in Pattern and Image Analysis, 59160K (30 August 2005); doi: 10.1117/12.615241
Show Author Affiliations
Gonzalo Urcid, INAOE (Mexico)

Published in SPIE Proceedings Vol. 5916:
Mathematical Methods in Pattern and Image Analysis
Jaakko T. Astola; Ioan Tabus; Junior Barrera, Editor(s)

© SPIE. Terms of Use
Back to Top