A polynomial time algorithm for generating neural networks for pattern classification: its stability properties and some test results

Authors:
Somnath Mukhopadhyay;Asim Roy;Lark Sang Kim;Sandeep Govil
Affiliations:
-;-;-;-
Venue:
Neural Computation
Year:
1993

Citing 0
Cited 2

Efficient adaptive learning for classification tasks with binary units

Neural Computation
Neural Network Based Classifers for a Vast Amount of Data

PAKDD '99 Proceedings of the Third Pacific-Asia Conference on Methodologies for Knowledge Discovery and Data Mining

Quantified Score

Hi-index	0.00

Visualization

Abstract

Polynomial time training and network design are two major issuesfor the neural network community. A new algorithm has beendeveloped that can learn in polynomial time and also design anappropriate network. The algorithm is for classification problemsand uses linear programing models to design and train the network.This paper summarizes the new algorithm, proves its stabilityproperties, and provides some computational results to demonstrateits potential.