Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1998-12-11
Physics
Condensed Matter
Disordered Systems and Neural Networks
11 pages, 4 figures
Scientific paper
10.1007/s100510050889
Equilibrium states of large layered neural networks with differentiable activation function and a single, linear output unit are investigated using the replica formalism. The quenched free energy of a student network with a very large number of hidden units learning a rule of perfectly matching complexity is calculated analytically. The system undergoes a first order phase transition from unspecialized to specialized student configurations at a critical size of the training set. Computer simulations of learning by stochastic gradient descent from a fixed training set demonstrate that the equilibrium results describe quantitatively the plateau states which occur in practical training procedures at sufficiently small but finite learning rates.
Ahr Martin
Biehl Michael
Urbanczik Robert
No associations
LandOfFree
Statistical physics and practical training of 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 Statistical physics and practical training of soft-committee machines, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Statistical physics and practical training of soft-committee machines will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-38397