Deep learning (DL) has recently changed the development of intelligent systems and is
widely adopted in many real-life applications. Despite their various benefits and potentials …

This chapter provides approaches to the problem of quantizing the numerical values in deep
Neural Network computations, covering the advantages/disadvantages of current methods …

This paper studies the Binary Neural Networks (BNNs) in which weights and activations are
both binarized into 1-bit values, thus greatly reducing the memory usage and computational …

Recent advances in machine learning by deep neural networks are significant. But using
these networks has been accompanied by a huge number of parameters for storage and …

Learning to synthesize data has emerged as a promising direction in zero-shot quantization
(ZSQ), which represents neural networks by low-bit integer without accessing any of the real …

Binary neural networks (BNNs) have received increasing attention due to their superior
reductions of computation and memory. Most existing works focus on either lessening the …

Convolutional network compression methods require training data for achieving acceptable
results, but training data is routinely unavailable due to some privacy and transmission …

Zero-shot quantization (ZSQ) is promising for compressing and accelerating deep neural
networks when the data for training full-precision models are inaccessible. In ZSQ, network …

This article focuses on filter-level network pruning. A novel pruning method, termed CLR-
RNF, is proposed. We first reveal a “long-tail” pruning problem in magnitude-based weight …

Network binarization emerges as one of the most promising compression approaches
offering extraordinary computation and memory savings by minimizing the bit-width …