Abstract | ||
---|---|---|
Results from working analog VLSI implementations of two different pulse stream neural network forms are reported. The circuits are rendered relatively invariant to processing variations, and the problem of cascadability of synapses to form large systems is addressed. A strategy for interchip communication of large numbers of neural states has been implemented in silicon and results are presented. The circuits demonstrated confront many of the issues that blight massively parallel analog systems, and offer solutions. |
Year | DOI | Venue |
---|---|---|
1992 | 10.1109/72.129411 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
integrated pulse stream neural,interchip communication,parallel analog system,offer solution,large number,large system,different pulse stream neural,network form,analog vlsi implementation,neural state,processing variation,signal processing,neural networks,neural network,synapses,analog circuits,amplitude modulation,neural nets,very large scale integration,silicon,pulse width modulation,process variation,vlsi | Signal processing,Analogue electronics,Telecommunications,Computer science,Massively parallel,Artificial intelligence,Artificial neural network,Very-large-scale integration,Integrated circuit,Computer engineering,Pulse-code modulation,Analog signal processing,Machine learning | Journal |
Volume | Issue | ISSN |
3 | 3 | 1045-9227 |
Citations | PageRank | References |
17 | 4.65 | 3 |
Authors | ||
6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alister Hamilton | 1 | 117 | 19.02 |
Murray, A.F. | 2 | 17 | 4.65 |
Baxter, D.J. | 3 | 17 | 4.65 |
S Churcher | 4 | 32 | 7.66 |
H. M. Reekie | 5 | 24 | 5.89 |
L Tarassenko | 6 | 17 | 4.65 |