Experimental exploration of the performance of binary networks
Atsunori Kanemura, Hiroshi Sawada, Takuya Wakisaka, Hitoshi Hano · 2017
Binary neural networks for object recognition are desirable especially for small and embedded systems because of their arithmetic and memory efficiency coming from the restriction of the bit-depth of network weights and activations. Neural networks in general have a tradeoff between the accuracy and efficiency in choosing a model architecture, and this tradeoff matters more for binary networks because of the limited bit-depth. This paper then examines the performance of binary networks by modifying architecture parameters (depth and width parameters) and reports the best-performing settings for specific datasets. These findings will be useful for designing binary networks for practical uses.