VC Dimension in Circuit Complexity

Authors:
Pascal Koiran
Affiliations:
-
Venue:
CCC '96 Proceedings of the 11th Annual IEEE Conference on Computational Complexity
Year:
1996

Citing 0
Cited 3

On the relevance of time in neural computation and learning

Theoretical Computer Science
Circuits versus Trees in Algebraic Complexity

STACS '00 Proceedings of the 17th Annual Symposium on Theoretical Aspects of Computer Science
On the complexity of computing and learning with multiplicative neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

The main result of this paper is a Omega(n^{1/4}) lower bound on the size of a sigmoidal circuit computing a specific AC^0_2 function. This is the first lower bound for the computation model of sigmoidal circuits with unbounded weights. We also give upper and lower bounds for the same function in a few other computation models: circuits of AND/OR gates, threshold circuits, and circuits of piecewise-rational gates.