Product Unit Neural Networks with Constant Depth and Superlinear VC Dimension

Authors:
Michael Schmitt
Affiliations:
-
Venue:
ICANN '01 Proceedings of the International Conference on Artificial Neural Networks
Year:
2001

Citing 6
Cited 0

Product units: a computationally powerful and biologically plausible extension to backpropagation networks

Neural Computation
Lower Bound Methods and Separation Results for On-Line Learning Models

Machine Learning - Computational learning theory
Neural nets with superlinear VC-dimension

Neural Computation
Neural networks with quadratic VC dimension

Journal of Computer and System Sciences - Special issue: dedicated to the memory of Paris Kanellakis
Learning in Neural Networks: Theoretical Foundations

Learning in Neural Networks: Theoretical Foundations
On the complexity of computing and learning with multiplicative neural networks

Neural Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

It has remained an open question whether there exist product unit networks with constant depth that have superlinear VC dimension. In this paper we give an answer by constructing two-hidden-layer networks with this property. We further show that the pseudo dimension of a single product unit is linear. These results bear witness to the cooperative effects on the computational capabilities of product unit networks as they are used in practice.