Biologically Inspired Architecture of Feedforward Networks for Signal Classification

Authors:
Sarunas Raudys;Minija Tamosiunaite
Affiliations:
-;-
Venue:
Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Year:
2000

Citing 6
Cited 2

Evolution and generalization of a single neurone: I. single-layer perceptron as seven statistical classifiers

Neural Networks
Structural change and development in real and artificial neural networks

Neural Networks
Neural Networks: A Comprehensive Foundation

Neural Networks: A Comprehensive Foundation
Structures of the Covariance Matrices in the Classifier Design

SSPR '98/SPR '98 Proceedings of the Joint IAPR International Workshops on Advances in Pattern Recognition
Towards a theory of early visual processing

Neural Computation
Backpropagation applied to handwritten zip code recognition

Neural Computation

Application of the Biologically Inspired Network for Electroencephalogram Analysis

Proceedings of the International Conference, 7th Fuzzy Days on Computational Intelligence, Theory and Applications
Multiple Classification Systems in the Context of Feature Extraction and Selection

MCS '02 Proceedings of the Third International Workshop on Multiple Classifier Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

The hypothesis is that in the lowest hidden layers of biological systems "local subnetworks" are smoothing an input signal. The smoothing accuracy may serve as a feature to feed the subsequent layers of the pattern classification network. The present paper suggests a multistage supervised and "unsupervised" training approach for design and training of multilayer feed-forward networks. Following to the methodology used in the statistical pattern recognition systems we split functionally the decision making process into two stages. In an initial stage, we smooth the input signal in a number of different ways and, in the second stage, we use the smoothing accuracy as a new feature to perform a final classification.