40 citations · 74 across the 11 of their papers we have counts for
5 papers · 1 filter
Hierarchical Weight Averaging for Deep Neural Networks
Xiaozhe Gu, Zixun Zhang, Yuncheng Jiang +4
Despite the simplicity, stochastic gradient descent (SGD)-like algorithms are successful in training deep neural networks (DNNs). Among various attempts to improve SGD, weight aver…
Statistical Modeling of Soft Error Influence on Neural Networks
Haitong Huang, Xinghua Xue, Cheng Liu +5
Soft errors in large VLSI circuits pose dramatic influence on computing- and memory-intensive neural network (NN) processing. Understanding the influence of soft errors on NNs is c…
RCT: Resource Constrained Training for Edge AI
Tian Huang, Tao Luo, Ming Yan +2
Neural networks training on edge terminals is essential for edge AI computing, which needs to be adaptive to evolving environment. Quantised models can efficiently run on edge devi…
Adaptive Precision Training for Resource Constrained Devices
Tian Huang, Tao Luo, Joey Tianyi Zhou
Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision traini…
EDCompress: Energy-Aware Model Compression for Dataflows
Zhehui Wang, Tao Luo, Joey Tianyi Zhou +1
Edge devices demand low energy consumption, cost and small form factor. To efficiently deploy convolutional neural network (CNN) models on edge device, energy-aware model compressi…