论文信息 - Stochastic vs. Deterministic Neural Networks for Pattern Recognition

Stochastic vs. Deterministic Neural Networks for Pattern Recognition

The performance of several neural network-like models for pattern recognition tasks are analyzed. A comparison based on recognition of random points in a multidimensional space is made among Backpropagation and different variations of Learning Vector Quantization and Boltzmann machine. The Boltzmann machine models and Hierarchical Learning Vector Quantization are found to perform well in the investigated tasks.

Kimmo Kaski | György Barna | K. Kaski | G. Barna

[1] Geoffrey E. Hinton,et al. Learning internal representations by error propagation , 1986 .

[2] D. Mitra,et al. Convergence and finite-time behavior of simulated annealing , 1986, Advances in Applied Probability.

[3] T. D. Harrison,et al. Boltzmann machines for speech recognition , 1986 .

[4] V. Cerný. Thermodynamical approach to the traveling salesman problem: An efficient simulation algorithm , 1985 .

[5] J J Hopfield,et al. Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6] C. D. Gelatt,et al. Optimization by Simulated Annealing , 1983, Science.

[7] Carsten Peterson,et al. A Mean Field Theory Learning Algorithm for Neural Networks , 1987, Complex Syst..

[8] Kimmo Kaski,et al. Variations on the Boltzmann machine , 1989 .

[9] Carsten Peterson,et al. Explorations of the mean field theory learning algorithm , 1989, Neural Networks.

[10] Geoffrey E. Hinton,et al. A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[11] Emile H. L. Aarts,et al. Simulated Annealing: Theory and Applications , 1987, Mathematics and Its Applications.

[12] Teuvo Kohonen,et al. Statistical pattern recognition with neural networks , 1988, Neural Networks.