Maximum entropy deconvolver circuit based on neural net principles
作者： Martin C. Peckerar , Christie R. K. Marrian
DOI:
关键词:
摘要: Disclosed are two modifications of the Tank-Hopfield circuit, each which enables deconvolution a signal in presence noise. In embodiment, circuit is modified so that equation for total energy reduces to one term representing convolution and another information theoretic (or Shannon) entropy. Thus, finding its global minimum state, inherently identifies an optimal estimate deconvoluted input without
lens.org 参考文章(8)
Edward G. Spencer, Computing apparatus comprising a programmable resistor ,(1987)
Stephen I. Gallant, Matrix controlled expert system producible from examples ,(1985)
John J. Hopfield, Electronic network for collective decision based on large number of connections between signals ,(1985)
David Kleinfeld, Temporal sequences with neural networks ,(1986)
D. Tank, J. Hopfield, Simple 'neural' optimization networks: An A/D converter, signal decision circuit, and a linear programming circuit IEEE Transactions on Circuits and Systems. ,vol. 33, pp. 533- 541 ,(1986) , 10.1109/TCS.1986.1085953
J. J. Hopfield, Neurons with graded response have collective computational properties like those of two-state neurons. Proceedings of the National Academy of Sciences of the United States of America. ,vol. 81, pp. 3088- 3092 ,(1984) , 10.1073/PNAS.81.10.3088
John Stewart Denker, A highly parallel computation network with normalized speed of response ,(1986)