9 citations · 9 across the 1 of their papers we have counts for
6 papers
Multilayer neural networks with extensively many hidden units
Michal Rosen-Zvi, Andreas Engel, Ido Kanter
The information processing abilities of a multilayer neural network with a number of hidden units scaling as the input dimension are studied using statistical mechanics methods. Th…
Correlations between hidden units in multilayer neural networks and replica symmetry breaking
D. Malzahn, A. Engel
We consider feed-forward neural networks with one hidden layer, tree architecture and a fixed hidden-to-output Boolean function. Focusing on the saturation limit of the storage pro…
A multifractal phase-space analysis of perceptrons with biased patterns
J. Berg, A. Engel
We calculate the multifractal spectrum of the partition of the coupling space of a perceptron induced by random input-output pairs with non-zero mean. From the results we infer the…
Storage capacity of correlated perceptrons
D. Malzahn, A. Engel, I. Kanter
We consider an ensemble of single-layer perceptrons exposed to random inputs and investigate the conditions under which the couplings of these perceptrons can be chosen such th…
On the VC-dimension of neural networks with binary weights
S. Mertens, A. Engel
We investigate the VC-dimension of the perceptron and simple two-layer networks like the committee- and the parity-machine with weights restricted to values . For binary inpu…
Multifractality and percolation in the coupling space of perceptrons
M. Weigt, A. Engel
The coupling space of perceptrons with continuous as well as with binary weights gets partitioned into a disordered multifractal by a set of random input patterns. The multi…