Title | ||
---|---|---|
High-Accuracy Mixed-Signal VLSI for Weight Modification in Contrastive Divergence Learning |
Abstract | ||
---|---|---|
This paper presents an approach to on-chip, unsupervised learning. A circuit capable of changing a neuron's synaptic weight with great accuracy is described and experimental results from its aVLSI implementation in a 0.6碌m CMOS process are shown and discussed. We consider its use in the "contrastive divergence" learning scheme of the Product of Experts (PoE) architecture. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1007/3-540-46084-5_69 | ICANN |
Keywords | Field | DocType |
high-accuracy mixed-signal vlsi,contrastive divergence learning,weight modification,great accuracy,synaptic weight,unsupervised learning,m cmos process,contrastive divergence,avlsi implementation,product of experts,chip | Computer science,Cmos process,Learning rule,Product of experts,Unsupervised learning,Artificial intelligence,Contrastive divergence,Artificial neural network,Mixed signal vlsi,Synaptic weight | Conference |
Volume | ISSN | ISBN |
2415 | 0302-9743 | 3-540-44074-7 |
Citations | PageRank | References |
1 | 0.47 | 5 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Patrice Fleury | 1 | 15 | 2.72 |
Alan F. Murray | 2 | 642 | 148.88 |
H. Martin Reekie | 3 | 23 | 12.58 |