Loading...
Please wait, while we are loading the content...
Similar Documents
On the vc-dimension of neural networks with binary weights (1996).
| Content Provider | CiteSeerX |
|---|---|
| Author | Mertens, S. Engel, A. |
| Abstract | Abstract: We investigate the VC-dimension of the perceptron and simple two-layer networks like the committee- and the parity-machine with weights restricted to values ±1. For binary inputs, the VC-dimension is determined by atypical pattern sets, i.e. it cannot be found by replica analysis or numerical Monte Carlo sampling. For small systems, exhaustive enumerations yield exact results. For systems that are too large for enumerations, number theoretic arguments give lower bounds for the VC-dimension. For the Ising perceptron, the VC-dimension is probably larger than N/2. |
| File Format | |
| Publisher Date | 1996-01-01 |
| Access Restriction | Open |
| Subject Keyword | Binary Weight Neural Network Atypical Pattern Set Replica Analysis Binary Input Simple Two-layer Network Exhaustive Enumeration Numerical Monte Carlo Sampling Ising Perceptron Small System Exact Result Number Theoretic Argument |
| Content Type | Text |
| Resource Type | Article |
