Bounds on learning in polynomial time

Details Bounds on learning in polynomial time Bounds on learning in polynomial time

1997-05-26

arxiv.org/abs/cond-mat/9705259v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

12 pages Latex with 8 eps figures

Scientific paper

The performance of large neural networks can be judged not only by their storage capacity but also by the time required for learning. A polynomial learning algorithm with learning time $\sim N^2$ in a network with $N$ units might be practical whereas a learning time $\sim e^N$ would allow rather small networks only. The question of absolute storage capacity $\alpha_c$ and capacity for polynomial learning rules $\alpha_p$ is discussed for several feed-forward architectures, the perceptron, the binary perceptron, the committee machine and a perceptron with fixed weights in the first layer and adaptive weights in the second layer. The analysis is based partially on dynamic mean field theory which is valid for $N\to\infty$. Especially for the committee machine a value $\alpha_p$ considerably lower than the capacity predicted by replica theory or simulations is found. This discrepancy is resolved by new simulations investigating the learning time dependence and revealing subtleties in the definition of the capacity.

Affiliated with

Also associated with

No associations

Rating

Bounds on learning in polynomial time 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 Bounds on learning in polynomial time, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Bounds on learning in polynomial time will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-560830