Electronic neural networks for global optimizationAn electronic neural network with feedback architecture, implemented in analog custom VLSI is described. Its application to problems of global optimization for dynamic assignment is discussed. The convergence properties of the neural network hardware are compared with computer simulation results. The neural network's ability to provide optimal or near optimal solutions within only a few neuron time constants, a speed enhancement of several orders of magnitude over conventional search methods, is demonstrated. The effect of noise on the circuit dynamics and the convergence behavior of the neural network hardware is also examined.
Document ID
19910035019
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Thakoor, A. P. (Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)
Moopenn, A. W. (Jet Propulsion Lab., California Inst. of Tech. Pasadena, CA, United States)