19 citations · 38 across the 6 of their papers we have counts for
5 papers
Nesting Forward Automatic Differentiation for Memory-Efficient Deep Neural Network Training
Cong Guo, Yuxian Qiu, Jingwen Leng +6
An activation function is an element-wise mathematical function and plays a crucial role in deep neural networks (DNN). Many novel and sophisticated activation functions have been…
SQuant: On-the-Fly Data-Free Quantization via Diagonal Hessian Approximation
Cong Guo, Yuxian Qiu, Jingwen Leng +6
Quantization of deep neural networks (DNN) has been proven effective for compressing and accelerating DNN models. Data-free quantization (DFQ) is a promising approach without the o…
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Cong Guo, Bo Yang Hsueh, Jingwen Leng +7
Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weig…
Ptolemy: Architecture Support for Robust Deep Learning
Yiming Gan, Yuxian Qiu, Jingwen Leng +2
Deep learning is vulnerable to adversarial attacks, where carefully-crafted input perturbations could mislead a well-trained Deep Neural Network to produce incorrect results. Today…
Adversarial Defense Through Network Profiling Based Path Extraction
Yuxian Qiu, Jingwen Leng, Cong Guo +4
Recently, researchers have started decomposing deep neural network models according to their semantics or functions. Recent work has shown the effectiveness of decomposed functiona…