Abstract | ||
---|---|---|
This paper proposes energy-efficient approximate multipliers based on the Mitchell's log multiplication, optimized for performing inferences on convolutional neural networks (CNN). Various design techniques are applied to the log multiplier, including a fully-parallel LOD, efficient shift amount calculation, and exact zero computation. Additionally, the truncation of the operands is studied to cre... |
Year | DOI | Venue |
---|---|---|
2019 | 10.1109/TC.2018.2880742 | IEEE Transactions on Computers |
Keywords | Field | DocType |
Approximation algorithms,Logic gates,Training,Energy consumption,Degradation,Convolutional neural networks | Truncation,Approximation algorithm,Convolutional neural network,Computer science,Parallel computing,Operand,Algorithm,Multiplier (economics),Multiplication,Energy consumption,Computation | Journal |
Volume | Issue | ISSN |
68 | 5 | 0018-9340 |
Citations | PageRank | References |
6 | 0.48 | 0 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
MIN SOO KIM | 1 | 82 | 16.71 |
Alberto A. Del Barrio | 2 | 78 | 14.49 |
Leonardo Tavares Oliveira | 3 | 6 | 0.48 |
Román Hermida | 4 | 89 | 15.34 |
Bagherzadeh, N. | 5 | 215 | 24.07 |