93 citations · 140 across the 13 of their papers we have counts for
5 papers · 1 filter
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…
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…
Multi-Modal Hybrid Deep Neural Network for Speech Enhancement
Zhenzhou Wu, Sunil Sivadas, Yong Kiam Tan +2
Deep Neural Networks (DNN) have been successful in en- hancing noisy speech signals. Enhancement is achieved by learning a nonlinear mapping function from the features of the corru…
Transfer Hashing with Privileged Information
Joey Tianyi Zhou, Xinxing Xu, Sinno Jialin Pan +3
Most existing learning to hash methods assume that there are sufficient data, either labeled or unlabeled, on the domain of interest (i.e., the target domain) for training. However…
Simple and Efficient Learning using Privileged Information
Xinxing Xu, Joey Tianyi Zhou, IvorW. Tsang +3
The Support Vector Machine using Privileged Information (SVM+) has been proposed to train a classifier to utilize the additional privileged information that is only available in th…