21 citations · 78 across the 12 of their papers we have counts for
Showing cond-mat.dis-nnShow all
3 papers · 1 filter
cond-mat.dis-nn1999★ 2 cited
Noisy regression and classification with continuous multilayer networks
Martin Ahr, Michael Biehl, Robert Urbanczik
We investigate zero temperature Gibbs learning for two classes of unrealizable rules which play an important role in practical applications of multilayer neural networks with diffe…
cond-mat.dis-nn1999★ 4 cited
Weight decay induced phase transitions in multilayer neural networks
M. Ahr, M. Biehl, E. Schloesser
We investigate layered neural networks with differentiable activation function and student vectors without normalization constraint by means of equilibrium statistical physics. We…
cond-mat.dis-nn1998★ 21 cited
Statistical physics and practical training of soft-committee machines
Martin Ahr, Michael Biehl, Robert Urbanczik
Equilibrium states of large layered neural networks with differentiable activation function and a single, linear output unit are investigated using the replica formalism. The quenc…