Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1999-01-19
Physics
Condensed Matter
Disordered Systems and Neural Networks
7 pages, 7 figures
Scientific paper
10.1088/0305-4470/32/27/301
We investigate layered neural networks with differentiable activation function and student vectors without normalization constraint by means of equilibrium statistical physics. We consider the learning of perfectly realizable rules and find that the length of student vectors becomes infinite, unless a proper weight decay term is added to the energy. Then, the system undergoes a first order phase transition between states with very long student vectors and states where the lengths are comparable to those of the teacher vectors. Additionally in both configurations there is a phase transition between a specialized and an unspecialized phase. An anti-specialized phase with long student vectors exists in networks with a small number of hidden units.
Ahr Martin
Biehl Michael
Schloesser E.
No associations
LandOfFree
Weight decay induced phase transitions in multilayer neural networks 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 Weight decay induced phase transitions in multilayer neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Weight decay induced phase transitions in multilayer neural networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-668677