On the VC-dimension of neural networks with binary weights

Details On the VC-dimension of neural networks with binary weights On the VC-dimension of neural networks with binary weights

1996-08-29

arxiv.org/abs/cond-mat/9608156v1

Physics

Condensed Matter

12 pages, LaTeX2e, 7 figures (eps)

Scientific paper

10.1103/PhysRevE.55.4478

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 $\pm1$. 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 $N/2$.

Affiliated with

Also associated with

No associations

Rating

On the VC-dimension of neural networks with binary weights does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with On the VC-dimension of neural networks with binary weights, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and On the VC-dimension of neural networks with binary weights will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-283640