Storage capacity of correlated perceptrons

D. Malzahn, A. Engel, I. Kanter

Research output: Contribution to journalArticlepeer-review

4 Scopus citations


We consider an ensemble of K single-layer perceptrons exposed to random inputs and investigate the conditions under which the couplings of these perceptrons can be chosen such that prescribed correlations between the outputs occur. A general formalism is introduced using a multiperceptron cost function that allows one to determine the maximal number of random inputs as a function of the desired values of the correlations. Replica-symmetric results for K=2 and K=3 are compared with properties of two-layer networks of tree-structure and fixed Boolean function between hidden units and output. The results show which correlations in the hidden layer of multilayer neural networks are crucial for the value of the storage capacity.

Original languageEnglish
Pages (from-to)7369-7378
Number of pages10
JournalPhysical Review E
Issue number6
StatePublished - 1997


Dive into the research topics of 'Storage capacity of correlated perceptrons'. Together they form a unique fingerprint.

Cite this