Abstract | ||
---|---|---|
Editor’s note: This article considers the under-investigated problem of training neural networks based on stochastic computing. A new dynamic sign magnitude representation for symbols in ternary format {-1, 0, 1} facilitates learning while retaining SC’s benefits. —<i>John Hayes, University of Michigan</i> |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/MDAT.2021.3063356 | IEEE Design & Test |
Keywords | DocType | Volume |
Artificial neural networks,Training,Logic gates,Neural networks,Stochastic processes,Adders,Quantization (signal) | Journal | 38 |
Issue | ISSN | Citations |
6 | 2168-2356 | 0 |
PageRank | References | Authors |
0.34 | 0 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Amir Ardakani | 1 | 2 | 1.40 |
Arash Ardakani | 2 | 33 | 8.42 |
Warren J. Gross | 3 | 1106 | 113.38 |