학술논문
Spatial Correlation and Value Prediction in Convolutional Neural Networks
Document Type
Periodical
Author
Source
IEEE Computer Architecture Letters IEEE Comput. Arch. Lett. Computer Architecture Letters. 18(1):10-13 Jan, 2019
Subject
Language
ISSN
1556-6056
1556-6064
2473-2575
1556-6064
2473-2575
Abstract
Convolutional neural networks (CNNs) are a widely used form of deep neural networks, introducing state-of-the-art results for different problems such as image classification, computer vision tasks, and speech recognition. However, CNNs are compute intensive, requiring billions of multiply-accumulate (MAC) operations per input. To reduce the number of MACs in CNNs, we propose a value prediction method that exploits the spatial correlation of zero-valued activations within the CNN output feature maps, thereby saving convolution operations. Our method reduces the number of MAC operations by 30.4 percent, averaged on three modern CNNs for ImageNet, with top-1 accuracy degradation of 1.7 percent, and top-5 accuracy degradation of 1.1 percent.