No abstract

Convolutional neural networks have achieved remarkable improvements in image and video recognition but incur a heavy computational burden. To reduce the computational complexity of a convolutional neural network, this paper proposes an algorithm based on the Winograd minimal filtering algorithm and Strassen algorithm. Theoretical assessments of the proposed algorithm show that it can dramatically reduce computational complexity. Furthermore, the Visual Geometry Group (VGG) network is employed to evaluate the algorithm in practice. The results show that the proposed algorithm can provide the optimal performance by combining the savings of these two algorithms. It saves 75% of the runtime compared with the conventional algorithm.

This paper proposes a loop prediction encoding method for decreasing power consumption on instruction memory address bus. The loop prediction encoding is based on detecting and predicting loop programs. The experiment results show that our method can decrease switching activity up to 81.5% on average, with small overheads on performance and area.

No abstract