Abstract
Binary Neural Network (BNN) method is an extreme application of convolutional neural network (CNN) parameter quantization. As opposed to the original CNN methods which employed floating-point computation with full-precision weights and activations, BBN uses 1-bit activations and weights. With BBNs, a significant amount of storage, network complexity and energy consumption can be reduced, and neural networks can be implemented more efficiently in embedded applications. Unfortunately, binarization causes severe information loss. A gap still exists between full-precision CNN models and their binarized counterparts. The recent developments in BNN have led to a lot of algorithms and solutions that have helped address this issue. This article provides a full overview of recent developments in BNN. The present paper focuses exclusively on 1-bit activations and weights networks, as opposed to previous surveys in which low-bit works are mixed in. In this paper, we conduct a complete investigation of BNN's development from their predecessors to the latest BNN algorithms and techniques, presenting a broad design pipeline, and discussing each module's variants. Along the way, this paper examines BNN (a) purpose: their early successes and challenges; (b) BNN optimization: selected representative works that contain key optimization techniques; (c) deployment: open-source frameworks for BNN modeling and development; (d) terminal: efficient computing architectures and devices for BNN and (e) applications: diverse applications with BNN. Moreover, this paper discusses potential directions and future research opportunities for the latest BNN algorithms and techniques, presents a broad design pipeline, and discusses each module's variants.
Abstract (translated)
URL
https://arxiv.org/abs/2110.06804
