The Mode-Fisher pooling for time complexity optimization in deep convolutional neural networks

In this paper, we aim to improve the performance, time complexity and energy efficiency of deep convolutional neural networks (CNNs) by combining hardware and specialization techniques. Since the pooling step represents a process that contributes significantly to CNNs performance improvement, we propose theMode-Fisher poolingmethod. This form of pooling can potentially offer a very promising results in terms of improving feature extraction performance. The proposed method reduces significantly the data movement in the CNN and save up to 10% of total energy, without any performance penalty.