Experimental Studies of Analog Neural Networks
As. the levels of complexity in problems of scientific interest have escalated, our approach to solving these problems has historically been to find and use increasingly sophisticated and complicated solutions. We have been aided in this task by the explosive development of powerful, inexpensive, general purpose digital computers. Also, as the computational tools at our disposal have increased in power and affordability, we have applied them to more difficult problems. Whether the problems to be solved are driving the development of more powerful computers or vice versa is hard to say, but the coupling between the two is strong and the trend is clear.
KeywordsHide Layer Component Variation Hide Neuron Synaptic Weight Adaptive Network
Unable to display preview. Download preview PDF.
- B. Widrow and M. E. Hoff, Adaptive Switching Circuits, IRE WESCON Convention Record IRE, New York 96–104 (1960).Google Scholar
- B. Widrow and M. E. Hoff, Associative Storage and Retrieval of Dig-ital Information in Networks of Adaptive Neurons in Biological Pro-totypes and Synthetic Systems, Vol 1, E. E. Bernard and M. R. Kane (eds), Plenum Press, New York (1962).Google Scholar
- D. E. Rumelhart, G. E. Hinton and R. J. Williams, Learning In-ternal Representations by Error Propagation in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol 1, D. E. Rumelhart and J. L. McClelland (eds) MIT Press Cambridge MA (1986).Google Scholar
- Y. LeCun, Learning Process in an Asymmetric Threshold Network in Disordered Systems and Biological Organization, E. Bienenstock, F. Fogelman Soulie and G. Weisbuch (eds.), NATO ASI Series F, Vol. 20, Springer Verlag, Berlin (1986).Google Scholar
- S. Satyanarayana, Y. Tsividis and H. P. Graf, A Reconfigurable Analog VLSI Neural Network, to be published in: Advances in Neural Information Processing Systems 2, D. Touretzky, ed. Morgan Kaufmann (1990).Google Scholar
- M. A. Sivilotti, M. R. Emerling and C. A. Mead, VLSI Architecture for Implementation of Neural Networks, AIP Conf. Proc. No. 151: Neural Networks for Computing, J. S. Denker (ed), American Inst. Physics, New York (1986).Google Scholar
- R. C. Frye, E. A. Rietman and C. C. Wong, Back-Propagation Learn-ing in Neural Network Hardware, submitted IEEE Trans. Neural Net-works.Google Scholar
- A. Lapedes and R. Farber, Nonlinear Signal Processing Using Neural Networks: Prediction and System Modelling, Los Alamos National Laboratory Report No. LA-UR-87–2662.Google Scholar
- R. C. Frye, K. D. Cummings and E. A. Rietman, A Neural Network Approach to Proximity Effect Corrections in Electron Beam Lithog-raphy, Proc. SPIE Conf. Microlithography, San Jose, CA, Mar 7–9, (1990).Google Scholar
- W.T. Lynch, T. E. Smith and W. Fichtner, An Algorithm for Proximity Effect Correction with E-Beam Exposure, Int’I. Conf. on Microlithography, Microcircuit Engineering, pp 309–314, Grenoble (1982).Google Scholar
- K. D. Cummings, Determination of Proximity Parameters for Elec-tron Beam Lithography, AT&T Bell Laboratories Internal Memorandum.Google Scholar