Electronic Neural Networks For Global Optimization
| Autor: | Alexander W. Moopenn, Anilkumar P. Thakoor, Silvio P. Eberhardt |
|---|---|
| Rok vydání: | 1990 |
| Předmět: |
Very-large-scale integration
Theoretical computer science Quantitative Biology::Neurons and Cognition Artificial neural network Analogue electronics Computer science Time delay neural network Optimal control Computer Science::Hardware Architecture medicine.anatomical_structure Recurrent neural network medicine Electronic engineering Neuron Stochastic neural network Global optimization |
| Zdroj: | SPIE Proceedings. |
| ISSN: | 0277-786X |
| DOI: | 10.1117/12.969917 |
| Popis: | An 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|