Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Higher-order artificial neural networks

Technical Report ·
OSTI ID:5726498

The report investigates the storage capacity of an artificial neural network where the state of each neuron depends on quadratic correlations of all other neurons, i.e. a third order network. This is in contrast to a standard Hopfield network where the state of each single neuron depends on the state on every other neuron, without any correlations. The storage capacity of a third order network is larger than that for standard Hopfield by one order of N. However, the number of connections is also larger by an order of N. It is shown that the storage capacity per connection is identical for standard Hopfield and for this third order network.

Research Organization:
Foersvarets Forskningsanstalt, Linkoeping (Sweden). Huvudavdelning foer Informationsteknologi
OSTI ID:
5726498
Report Number(s):
PB-91-165316/XAB; FOA-C--30574-3.4
Country of Publication:
United States
Language:
English

Similar Records

Topics in neural networks
Thesis/Dissertation · Thu Dec 31 23:00:00 EST 1987 · OSTI ID:6988011

Neural network models for optical computing; Proceedings of the Meeting, Los Angeles, CA, Jan. 13, 14, 1988
Conference · Thu Dec 31 23:00:00 EST 1987 · OSTI ID:6385289

Phase transitions in dilute, locally connected neural networks
Journal Article · Wed Apr 15 00:00:00 EDT 1992 · Physical Review A. General Physics; (United States) · OSTI ID:7302754