Original Contribution: Classes of feedforward neural networks and their circuit complexity

Authors:
John S. Shawe-Taylor;Martin H. G. Anthony;Walter Kern
Affiliations:
Royal Holloway, University of London, UK;London School of Economics, University of London, UK;University of Twente, UK
Venue:
Neural Networks
Year:
1992

Citing 2
Cited 2

Monotone circuits for connectivity require super-logarithmic depth

STOC '88 Proceedings of the twentieth annual ACM symposium on Theory of computing
Lattices, mobius functions and communications complexity

SFCS '88 Proceedings of the 29th Annual Symposium on Foundations of Computer Science

Energy and fan-in of threshold circuits computing mod functions

TAMC'11 Proceedings of the 8th annual conference on Theory and applications of models of computation
Energy and fan-in of logic circuits computing symmetric Boolean functions

Theoretical Computer Science

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper aims to place neural networks in the context of boolean circuit complexity. We define appropriate classes of feedforward neural networks with specified fan-in, accuracy of computation and depth and using techniques of communication complexity proceed to show that the classes fit into a well-studied hierarchy of boolean circuits. Results cover both classes of sigmoid activation function networks and linear threshold networks. This provides a much needed theoretical basis for the study of the computational power of feedforward neural networks.