The limitations of deterministic Boltzmann machine learning
- 1 August 1993
- journal article
- Published by Taylor & Francis in Network: Computation in Neural Systems
- Vol. 4 (3) , 355-379
- https://doi.org/10.1088/0954-898x/4/3/007
Abstract
No abstract availableKeywords
This publication has 13 references indexed in Scilit:
- First- and Second-Order Methods for Learning: Between Steepest Descent and Newton's MethodNeural Computation, 1992
- Mean Field Theory Neural Networks for Feature Recognition, Content Addressable Memory and OptimizationConnection Science, 1991
- Associative memory in an analog iterated-map neural networkPhysical Review A, 1990
- Deterministic Boltzmann Learning Performs Steepest Descent in Weight-SpaceNeural Computation, 1989
- Learning algorithms and probability distributions in feed-forward and feed-back networksProceedings of the National Academy of Sciences, 1987
- TAP free energy structure of SK spin glassesJournal of Physics C: Solid State Physics, 1985
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984
- Digital dynamics and the simulation of magnetic systemsPhysical Review B, 1983
- Evidence for massless modes in the 'solvable model' of a spin glassJournal of Physics C: Solid State Physics, 1979
- Time-Dependent Statistics of the Ising ModelJournal of Mathematical Physics, 1963