Corpus ID: 15515421

A Mean Field Theory Learning Algorithm for N eu ral N etwor ks

@inproceedings{Peterson2006AMF,
  title={A Mean Field Theory Learning Algorithm for N eu ral N etwor ks},
  author={C. Peterson and James R. Anderson},
  year={2006}
}
Based on t he Boltzmann Machine concept, we derive a lear ning algorith m in which time-consuming stochastic measurements of correlations a re replaced by solutions to dete rminist ic mean field theory equ ations. T he method is applied to t he XOR (exclusive-or ), encoder, and line sym metry problems with substantial success. We observe speedup facto rs ranging from 10 to 30 for these ap plicat ions and a significantly bet ter learning perform an ce in general. 1. Motivation and results 1.1… Expand

References

SHOWING 1-10 OF 12 REFERENCES
“Neural” computation of decisions in optimization problems
TLDR
Results of computer simulations of a network designed to solve a difficult but well-defined optimization problem-the Traveling-Salesman Problem-are presented and used to illustrate the computational power of the networks. Expand
Neural networks and physical systems with emergent collective computational abilities.
  • J. Hopfield
  • Computer Science, Medicine
  • Proceedings of the National Academy of Sciences of the United States of America
  • 1982
TLDR
A model of a system having a large number of simple equivalent components, based on aspects of neurobiology but readily adapted to integrated circuits, produces a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. Expand
Learning internal representations by error propagation
This chapter contains sections titled: The Problem, The Generalized Delta Rule, Simulation Results, Some Further Generalizations, Conclusion
A Neuromorphic VLSI Lear ning System
  • Advanced Research in VLSI: Proceedings of the 1987 Stanford Confere nce
  • 1987
A Learn ing Algorit hm for Boltzmann Machi nes
  • Cognitive Science
  • 1985
Optimizat ion by Simu - lat ed Annealing
  • Biological Cybern etics
  • 1985
S cience
  • S cience
  • 1983
Hop fieldNeural Networks and phys ical systems wit h emergent collecti ve computational abilities
  • Proceedings of the Nat ional Academy of Science
  • 1982
Differentjal Eq uations, Dy namical Systems, an d Linear Algebra
  • Differentjal Eq uations, Dy namical Systems, an d Linear Algebra
  • 1974
Glauber , " Time - Dependent Sta . tistic s ofthe Ising Model
  • Journal of Mathematical Physics
  • 1963
...
1
2
...