References
- Battiti R. First- and second-order methods for learning: between steepest descent and Newton's method. Neural Comput. 1992; 4: 141–66
- Bray A J, Moore M A. Evidence for massless modes in the ‘solvable model’ of a spin glass. J. Phys. C: Solid State Phys. 1979; 12: L441–8
- Choi M Y, Huberman B A. Digital dynamics and the simulation of magnetic systems. Phys. Rev. B 1983; 28: 2547–54
- Freund Y, Haussler D. Unsupervised learning of distributions on binary vectors using two layer networks. Advances in Neural Information Processing Systems, J E Moody, S J Hanson, R P Lippmann. Morgan Kaufmann, San Mateo, CA 1992; vol 4: 912–9
- Galland C C. Learning in deteministic Boltzmann machine networks. University of Toronto. 1992, PhD Thesis
- Galland C C, Hinton G E. Deterministic Boltzmann learning in networks with asymmetric connectivity. Technical Report. CRG-TR-89-6, University of Toronto, Department of Computer Science. 1989
- Galland C C, Neal R M, Hinton G E. Unsupervised learning with the restricted ensemble Boltzmann machine. IEEE Trans. Neural Networks 1993, submitted
- Glauber R J. Time-dependent statistics of the Ising model. J. Math. Phys. 1963; 4: 294–307
- Hinton G E. Learning distributed representations of concepts. Proc. Eighth Annual Conference of the Cognitive Science Society. Erlbaum, Hillsdale, NJ 1986; 1–12
- Hinton G E. Deterministic Boltzmann learning performs steepest descent in weight-space. Neural Comput. 1989; 1: 143–150
- Hinton G E, Sejnowski T J. Parallel distributed processing: explorations in the microstructure of cognition. Learning and relearning in Boltzmann machines, D E Rumelhart, J L McClelland. MIT Press, Cambridge, MA 1986; 282–317, The PDP Research Group
- Hopfield J J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Natl Acad. Sci. 1984; 81: 3088–92
- Hopfield J J. Learning algorithms and probability distributions in feed-forward and feed-back networks. Proc. Natl Acad. Sci. 1987; 84: 8429–33
- Le Cun Y, Denker J S. A new learning rule for recurrant networks. Proc. Conf. on Neural Networks for Computing, Snowbird, UT, 1991
- Marcus C M, Waugh F R, and Westervelt R M. Associative memory in an analog iterated-map neural network. Phys. Rev. A 1990; 41: 3355–64
- Movellan J R. contrastive Hebbian learning in the continuous Hopfield model. Proc.1990 Connectionist Models Summer School. Morgan Kaufmann, San Mateo, CA 1990
- Nemoto K, Takayama H TAP. Free energy structure of SK spin glasses. J. Phys. C: Solid State Phys. 1985; 18: L529–35
- Peterson C. Mean field theory neural networks for feature recognition, content addressable memory and optimization. Connect. Sci. 1991; 3: 3–33
- Peterson C, Anderson J R. A mean field theory learning algorithm for neural networks. Complex Syst. 1987; 1: 995–1019
- Pineda F J, Baldi P. Contrastive learning and neural oscillations. Neural Comput. 1991; 3: 526–45
- Press W H, Flannery B P, Teukolsky S A, Vetterling W T. Numerical Recipes in C. Cambridge University Press, Cambridge 1988; 353–97
- Thouless D J, Anderson P W, Palmer R G. Solution of ‘Solvable model of a Spin Glass’. Phil. Mag. 1977; 35: 593–601
- Waugh F R, Marcus C M, Westervelt R M. Fixed-point attractors in analog neural computation. Phys. Rev. Lett. 1990; 64: 1986–9