3 papers
cond-mat.dis-nn2002
Statistical Physics of Feedforward Neural Networks
Robert Urbanczik
The article is a lightly edited version of my habilitation thesis at the University Wuerzburg. My aim is to give a self contained, if concise, introduction to the formal methods us…
cond-mat.dis-nn2001
Learning multilayer perceptrons efficiently
C. Bunzmann, M. Biehl, R. Urbanczik
A learning algorithm for multilayer perceptrons is presented which is based on finding the principal components of a correlation matrix computed from the example inputs and their t…
cond-mat1997
On-line learning in a discrete state space
W. Kinzel, R. Urbanczik
On-line learning of a rule given by an N-dimensional Ising perceptron, is considered for the case when the student is constrained to take values in a discrete state space of size $…