Complex Boltzmann networks and one stage learning

The author considers the discrete Boltzmann net with complex activations and weights. In particular he shows the following: it is possible to define an energy Hamiltonian with properties similar to the one in the real case; with appropriate clamping of a set of pattern units, the usual two-stage lea...

Full description

Saved in:
Bibliographic Details
Published in[Proceedings 1992] IJCNN International Joint Conference on Neural Networks Vol. 4; pp. 791 - 795 vol.4
Main Author Rager, J.E.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1992
Subjects
Clamps
Computational linguistics
Computer networks
Computer science
Educational institutions
Glass
Laboratories
Mathematics
Neural networks
Optical computing
Online AccessGet full text

Cover

More Information
Summary:The author considers the discrete Boltzmann net with complex activations and weights. In particular he shows the following: it is possible to define an energy Hamiltonian with properties similar to the one in the real case; with appropriate clamping of a set of pattern units, the usual two-stage learning can be accomplished in one stage; and this model is still strongly related to the physical Spin Glass model, although not to the simple Ising model. Simulations, extensions, and future work are discussed.< >
ISBN:0780305590
9780780305595
DOI:10.1109/IJCNN.1992.227221