Parallel computations and committee constructions

Authors:
V. D. Mazurov;M. Yu. Khachai
Affiliations:
Ural State University, Yekaterinburg, Russia and Institute of Mathematics and Mechanics, Ural Branch, Russian Academy of Sciences, Yekaterinburg, Russia;Ural State University, Yekaterinburg, Russia and Institute of Mathematics and Mechanics, Ural Branch, Russian Academy of Sciences, Yekaterinburg, Russia
Venue:
Automation and Remote Control
Year:
2007

Citing 4
Cited 1

Neural network design and the complexity of learning

Neural network design and the complexity of learning
Complexity Results on Learning by Neural Nets

Machine Learning
Original Contribution: Training a 3-node neural network is NP-complete

Neural Networks
The Hardness of 3 - Uniform Hypergraph Coloring

FOCS '02 Proceedings of the 43rd Symposium on Foundations of Computer Science

Computational complexity of recognition learning procedures in the class of piecewise-linear committee decision rules

Automation and Remote Control

Quantified Score

Hi-index	0.00

Visualization

Abstract

The paper reviewed the results bearing out the deep-seated relation between the parallel computations and learning procedures for the laminated neural networks one of whose formalizations is represented by the theory of committee constructions. Additionally, consideration was given to two combinatorial problems concerned with learning pattern recognition in the class of affine committees--the problem of verifying existence of a three-element affine separating committee and that of element-minimal affine separating committee. The first problem was shown to be N P-complete, whereas the second problem is N P-hard and does not belong to the Apx class.