Over the past few years, larger and deeper neural network models, particularly convolutional
neural networks (CNNs), have consistently advanced state-of-the-art performance across …

Network pruning is one of the chief means for improving the computational efficiency of
Deep Neural Networks (DNNs). Pruning-based methods generally discard network kernels …

近年来, 随着传感器, 采集装置, 感知终端的规模化部署, 以及人工智能, 5G, 北斗等新技术的融合
应用, 智能巡检, 在线监测, 需求响应等电力物联网应用产生海量感知数据 …

Neural network quantization has achieved a high compression rate using a fixed low bit-
width representation of weights and activations while maintaining the accuracy of the high …

The deployment of Deep Neural Network (DNN)-based networks on resource-constrained
devices remains a significant challenge due to their high computational and parameter …

Despite the popularization of deep neural networks (DNNs) in many fields, it is still
challenging to deploy state-of-the-art models to resource-constrained devices due to high …

The prohibitive complexity of convolutional neural networks (CNNs) has triggered an
increasing demand for network simplification. To this end, one natural solution is to remove …

Abstract Deep Convolutional Neural Networks (CNNs), continue to demonstrate remarkable
performance across various tasks. However, their computational demands and energy …

Pruning has recently become ever-important research to compress deep neural networks.
Previous pruning methods focus on removing filters, channels, or weights to reduce the …

Deep learning has revolutionized computing in many real-world applications, arguably due
to its remarkable performance and extreme convenience as an end-to-end solution …