Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1998-05-15
Physics
Condensed Matter
Disordered Systems and Neural Networks
8 pages, 4 figures
Scientific paper
10.1209/epl/i1998-00466-6
Equilibrium statistical physics is applied to layered neural networks with differentiable activation functions. A first analysis of off-line learning in soft-committee machines with a finite number (K) of hidden units learning a perfectly matching rule is performed. Our results are exact in the limit of high training temperatures. For K=2 we find a second order phase transition from unspecialized to specialized student configurations at a critical size P of the training set, whereas for K > 2 the transition is first order. Monte Carlo simulations indicate that our results are also valid for moderately low temperatures qualitatively. The limit K to infinity can be performed analytically, the transition occurs after presenting on the order of N K examples. However, an unspecialized metastable state persists up to P= O (N K^2).
Ahr Martin
Biehl Michael
Schloesser E.
No associations
LandOfFree
Phase transitions in soft-committee machines 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 Phase transitions in soft-committee machines, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Phase transitions in soft-committee machines will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-1159