Product Unit Neural Networks with Constant Depth and Superlinear VC Dimension

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.

• Type: Conference
• Year: 2001
• Where: ICANN
• Authors: Michael Schmitt
• Keywords: ICANN 2001, Neural Networks, Product Unit, Single Product Unit, Superlinear Vc Dimension