Abstract | ||
---|---|---|
The Hopfield architecture can be utilized in the VLSI implementation of several important optimization functions. A description is given of the properties of local minima in the energy function of Hopfield networks. A novel design technique to eliminate such local minima has been developed. The neural-based analog-to-digital converter is used as an example to demonstrate this design technique. Experimental results agree well with theoretical calculations on the output characteristics of the analog-to-digital converter.<> |
Year | DOI | Venue |
---|---|---|
1988 | 10.1109/ICNN.1988.23827 | San Diego, CA, USA |
Keywords | Field | DocType |
vlsi,analogue-digital conversion,network synthesis,neural nets,optimisation,adc,hopfield network,energy function,local minima,neural-based analog-to-digital converter,optimization circuits,very large scale integration,neural networks | Topology,Computer science,Network synthesis filters,Maxima and minima,Artificial intelligence,Electronic circuit,Artificial neural network,Hopfield network,Very-large-scale integration | Conference |
Citations | PageRank | References |
4 | 1.76 | 0 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lee, B.W. | 1 | 15 | 2.94 |
B. J. Sheu | 2 | 129 | 28.40 |