论文信息 - Integer-weight neural nets

Integer-weight neural nets

Integer-weight neural nets (IWNN) are better suited for hardware implementation than their real-weight analogues. The authors present a learning procedure for generating multilayer IWNNs having all weights in the set {–3, –2, –1, 0, 1, 2, 3}. The performance of this procedure was evaluated on XOR, encoder/decoder and the MONK benchmark. The IWNNs were found to be as capable as their real-weight counterparts with regard to generalisation performance.

Evor L. Hines | A. H. Khan

[1] Jay S. Patel,et al. Factors influencing learning by backpropagation , 1988, IEEE 1988 International Conference on Neural Networks.

[2] H. John Caulfield,et al. Weight discretization paradigm for optical neural networks , 1990, Other Conferences.

[3] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[4] K. P. Unnikrishnan,et al. Alopex: A Correlation-Based Learning Algorithm for Feedforward and Recurrent Neural Networks , 1994, Neural Computation.

[5] D.R. Hush,et al. Progress in supervised neural networks , 1993, IEEE Signal Processing Magazine.