Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1999-09-29
Physics
Condensed Matter
Disordered Systems and Neural Networks
28 pages, LaTeX
Scientific paper
We apply a general theory describing the dynamics of supervised learning in layered neural networks in the regime where the size p of the training set is proportional to the number of inputs N, as developed in a previous paper, to several choices of learning rules. In the case of (on-line and batch) Hebbian learning, where a direct exact solution is possible, we show that our theory provides exact results at any time in many different verifiable cases. For non-Hebbian learning rules, such as Perceptron and AdaTron, we find very good agreement between the predictions of our theory and numerical simulations. Finally, we derive three approximation schemes aimed at eliminating the need to solve a functional saddle-point equation at each time step, and assess their performance. The simplest of these schemes leads to a fully explicit and relatively simple non-linear diffusion equation for the joint field distribution, which already describes the learning dynamics surprisingly well over a wide range of parameters.
Coolen Anthony C. C.
Saad David
No associations
LandOfFree
Dynamics of Learning with Restricted Training Sets II: Tests and Applications 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 Dynamics of Learning with Restricted Training Sets II: Tests and Applications, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Dynamics of Learning with Restricted Training Sets II: Tests and Applications will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-548307