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 …

Waveform design with constant modulus constraint (CMC) is of great importance in multiple-
input–multiple-output radar systems. Both the relaxations in model-based waveform design …

Controllable image denoising aims to generate clean samples with human perceptual priors
and balance sharpness and smoothness. In traditional filter-based denoising methods, this …

While federated learning (FL) systems often utilize quantization to battle communication and
computational bottlenecks they have heretofore been limited to deploying fixed-precision …

Mixed-precision quantization mostly predetermines the model bit-width settings before
actual training due to the non-differential bit-width sampling process, obtaining suboptimal …

CNN model computation on edge devices is tightly restricted to the limited resource and
power budgets, which motivates the low-bit quantization technology to compress CNN …

In the realm of deep learning, the advent of large-scale pre-trained models has significantly
advanced computer vision and natural language processing. However, deploying these …

Quantized neural networks employ reduced precision representations for both weights and
activations. This quantization process significantly reduces the memory requirements and …

Research on deep learning accelerators has focused on inference tasks to improve
performance by means of maximally utilizing sparsity and quantization. Unlike CNN-only …

It has been proven that, compared to using 32-bit floating-point numbers in the training
phase, Deep Convolutional Neural Networks (DCNNs) can operate with low-precision …