Classifiers for decoding patterns in the response of an artificial retina

We present a neural classifier able to reliably determine the correlation between elementary image patterns and the characteristics of the chaotic regime of an artificial retina based on nonlinear dynamics. While the classifier is a typical neural one, it has the role of completing the neural retina...

Full description

Saved in:
Bibliographic Details
Main Authors: Teodorescu, Horia-Nicolai L., Hulea, Mircea Gh
Format: Conference Proceeding
Language:English
Subjects:
Biological neural networks
Chaos
Neurons
Pattern recognition
Retina
Sensors
Training
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present a neural classifier able to reliably determine the correlation between elementary image patterns and the characteristics of the chaotic regime of an artificial retina based on nonlinear dynamics. While the classifier is a typical neural one, it has the role of completing the neural retina with the equivalent of the upper layers of neurons in the nervous system of mammals. Without this classification stage, the proper use of the retina is imperfect, hence the significance of reporting on it. The performance of the classifier is discussed in relation to the application requirements. This paper represents a preliminary, abstracted version of a paper to be published in a journal.
DOI:10.1109/ISSCS.2013.6651168