Name
Title | ||
|---|---|---|
Power Reduction in CNN Pooling Layers with a Preliminary Partial Computation Strategy |
Abstract | ||
|---|---|---|
Convolutional neural networks (CNNs) are responsible for many recent successes in the computer vision field and are now the dominant approach for image classification. However, CNN-based methods perform many convolution operations and have high power consumption which makes them difficult to deploy on mobile devices. In this paper, we propose a new method to reduce CNN power consumption by simplifying computations before max-pooling layers. The proposed method estimates the output of the max-pooling layer by approximating the preceding convolutional layer with a preliminary partial computation. Then, the method performs a complementary computation to generate an exact convolution output only for the selected feature. We also present an analysis of the approximation parameters. Simulation results show that the proposed method reduces the power consumption by 21% and the silicon area by 19% with negligible degradation in classification accuracy for the CIFAR-10 dataset. |
Year | DOI | Venue |
|---|---|---|
2018 | 10.1109/NEWCAS.2018.8585433 | 2018 16th IEEE International New Circuits and Systems Conference (NEWCAS) |
Keywords | Field | DocType |
convolutional neural network,power consumption,classification accuracy,max-pooling | Microsoft Windows,Computer science,Convolutional neural network,Convolution,Pooling,Algorithm,Electronic engineering,Mobile device,Contextual image classification,Power consumption,Computation | Conference |
ISSN | ISBN | Citations |
2472-467X | 978-1-5386-4860-5 | 1 |
PageRank | References | Authors |
0.36 | 0 | 4 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Mehdi Ahmadi | 1 | 5 | 0.81 |
| Shervin Vakili | 2 | 38 | 4.79 |
| J. M. Pierre Langlois | 3 | 87 | 20.69 |
| Warren J. Gross | 4 | 1106 | 113.38 |