Perceptron training algorithms designed using discrete-time control Liapunov functions

Authors:
Oumar Diene;Amit Bhaya
Affiliations:
Center of Engineering, Modeling and Applied Social Sciences, CECS/Federal University of ABC, Rua Catequese 242, 09090-400 Santo Andre, SP, Brazil;Department of Electrical Engineering, NACAD-COPPE/Federal University of Rio de Janeiro, P.O. Box 68504, 21945-970 Rio de Janeiro, RJ, Brazil
Venue:
Neurocomputing
Year:
2009

Citing 8
Cited 1

The mathematical foundations of learning machines

The mathematical foundations of learning machines
Support-Vector Networks

Machine Learning
Iterative Methods for Sparse Linear Systems

Iterative Methods for Sparse Linear Systems
Control Perspectives on Numerical Algorithms And Matrix Problems (Advances in Design and Control) (Advances in Design and Control 10)

Control Perspectives on Numerical Algorithms And Matrix Problems (Advances in Design and Control) (Advances in Design and Control 10)
New Support Vector Algorithms

Neural Computation
Support vector classifiers via gradient systems with discontinuous righthand sides

Neural Networks
Adaptive conjugate gradient algorithm for perceptron training

Neurocomputing
Adaptive Ho-Kashyap rules for perceptron training

IEEE Transactions on Neural Networks

Conjugate gradient and steepest descent constant modulus algorithms applied to a blind adaptive array

Signal Processing

Quantified Score

Hi-index	0.01

Visualization

Abstract

Perceptrons, proposed in the seminal paper McCulloch-Pitts of 1943, have remained of interest to neural network community because of their simplicity and usefulness in classifying linearly separable data and can be viewed as implementing iterative procedures for ''solving'' linear inequalities. Gradient descent and conjugate gradient methods, normally used for linear equalities, can be used to solve linear inequalities by simple modifications that have been proposed in the literature but not been analyzed completely. This paper applies a recently proposed control-inspired approach to the design of iterative steepest descent and conjugate gradient algorithms for perceptron training in batch mode, by regarding certain parameters of the training/algorithm as controls and then using a control Liapunov technique to choose appropriate values of these parameters.