论文信息 - FPGA IMPLEMENTATION OF BIDIRECTIONAL ASSOCIATIVE MEMORY US I N G SI M U LTAN EO US P ERTU R BAT IO N

FPGA IMPLEMENTATION OF BIDIRECTIONAL ASSOCIATIVE MEMORY US I N G SI M U LTAN EO US P ERTU R BAT IO N

Recurrent neural networks have interesting properties and can handle dynamic information processing unlike the ordi- nary feedforward neural networks. Bidirectional associative mem- ory (BAM) is a typical recurrent network. Ordinarily, weights of the BAM are determined by the Hebb's learning. In this paper, a recursive learning scheme for BAM is proposed and its hardware implementation is described. The learning scheme is applicable to analogue BAM as well. A simulation result and details of the implementation are shown.

Yutaka Maeda | M. Wakamura | Y. Maeda | M. Wakamura

[1] Yutaka Maeda,et al. FPGA implementation of a pulse density neural network with learning ability using simultaneous perturbation , 2003, IEEE Trans. Neural Networks.

[2] J. Spall. A Stochastic Approximation Technique for Generating Maximum Likelihood Parameter Estimates , 1987, 1987 American Control Conference.

[3] Bart Kosko,et al. Neural networks and fuzzy systems , 1998 .

[4] J. Spall. Multivariate stochastic approximation using a simultaneous perturbation gradient approximation , 1992 .

[5] Gert Cauwenberghs,et al. A Fast Stochastic Error-Descent Algorithm for Supervised Learning and Optimization , 1992, NIPS.

[6] Yutaka Maeda,et al. A learning rule of neural networks via simultaneous perturbation and its hardware implementation , 1995, Neural Networks.

[7] Yutaka Maeda,et al. Learning Rules for Recurrent Neural Networks using Perturbation and their Application to Neuro-Control , 1993 .