12 search results - page 1 / 3 » VC Dimension Bounds for Product Unit Networks |
IJCNN
2000
IEEE
13 years 8 months ago
2000
IEEE
A product unit is a formal neuron that multiplies its input values instead of summingthem. Furthermore, it has weights acting as exponents instead of being factors. We investigate...
ICANN
2001
Springer
13 years 8 months ago
2001
Springer
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 cons...
NIPS
1998
13 years 5 months ago
1998
EUROCOLT
1997
Springer
13 years 8 months ago
1997
Springer
Most of the work on the Vapnik-Chervonenkis dimension of neural networks has been focused on feedforward networks. However, recurrent networks are also widely used in learning app...
COLT
1993
Springer
13 years 8 months ago
1993
Springer
We consider the problem of learning in multilayer feed-forward networks of linear threshold units. We show that the Vapnik-Chervonenkis dimension of the class of functions that ca...