论文信息 - Acceleration for both Boltzmann machine learning and mean field theory learning

Acceleration for both Boltzmann machine learning and mean field theory learning

Novel learning algorithms for both the Boltzmann machine (BM) and mean field theory (MFT) are proposed to accelerate learning. The effectiveness of the proposed MFT algorithm is confirmed by computer simulations. It accelerates convergence: for example, the proposed MFT algorithm is more than twice as fast as the conventional MFT algorithm when the learning constant eta is 0.1 or less. In addition, it is shown that the proposed algorithm is less sensitive to eta . MFT is more biologically plausible and more suitable for VLSI implementation than the other supervised learning paradigms, and it can also be used as a content addressable memory.<<ETX>>

Masafumi Hagiwara

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

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

[3] Geoffrey E. Hinton,et al. Learning and relearning in Boltzmann machines , 1986 .

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

[5] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[6] T. Kohonen,et al. Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[7] Geoffrey E. Hinton. Deterministic Boltzmann Learning Performs Steepest Descent in Weight-Space , 1989, Neural Computation.

[8] Geoffrey E. Hinton,et al. Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[9] Geoffrey E. Hinton,et al. Learning symmetry groups with hidden units: beyond the perceptron , 1986 .

[10] Terrence J. Sejnowski,et al. Analysis of hidden units in a layered network trained to classify sonar targets , 1988, Neural Networks.

[11] Masafumi Hagiwara. Novel backpropagation algorithm for reduction of hidden units and acceleration of convergence using artificial selection , 1990, 1990 IJCNN International Joint Conference on Neural Networks.