177 citations · 240 across the 11 of their papers we have counts for
12 papers
Towards Efficient Tensor Decomposition-Based DNN Model Compression with Optimization Framework
Miao Yin, Yang Sui, Siyu Liao +1
Advanced tensor decomposition, such as Tensor train (TT) and Tensor ring (TR), has been widely studied for deep neural network (DNN) model compression, especially for recurrent neu…
Towards Extremely Compact RNNs for Video Recognition with Fully Decomposed Hierarchical Tucker Structure
Miao Yin, Siyu Liao, Xiao-Yang Liu +2
Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model si…
Noise Injection-based Regularization for Point Cloud Processing
Xiao Zang, Yi Xie, Siyu Liao +2
Noise injection-based regularization, such as Dropout, has been widely used in image domain to improve the performance of deep neural networks (DNNs). However, efficient regulariza…
Doubly Residual Neural Decoder: Towards Low-Complexity High-Performance Channel Decoding
Siyu Liao, Chunhua Deng, Miao Yin +1
Recently deep neural networks have been successfully applied in channel coding to improve the decoding performance. However, the state-of-the-art neural channel decoders cannot ach…
Compressing Recurrent Neural Networks Using Hierarchical Tucker Tensor Decomposition
Miao Yin, Siyu Liao, Xiao-Yang Liu +2
Recurrent Neural Networks (RNNs) have been widely used in sequence analysis and modeling. However, when processing high-dimensional data, RNNs typically require very large model si…
PERMDNN: Efficient Compressed DNN Architecture with Permuted Diagonal Matrices
Chunhua Deng, Siyu Liao, Yi Xie +3
Deep neural network (DNN) has emerged as the most important and popular artificial intelligent (AI) technique. The growth of model size poses a key energy efficiency challenge for…
Embedding Compression with Isotropic Iterative Quantization
Siyu Liao, Jie Chen, Yanzhi Wang +2
Continuous representation of words is a standard component in deep learning-based NLP models. However, representing a large vocabulary requires significant memory, which can cause…
CAG: A Real-time Low-cost Enhanced-robustness High-transferability Content-aware Adversarial Attack Generator
Huy Phan, Yi Xie, Siyu Liao +2
Deep neural networks (DNNs) are vulnerable to adversarial attack despite their tremendous success in many AI fields. Adversarial attack is a method that causes the intended misclas…
CircConv: A Structured Convolution with Low Complexity
Siyu Liao, Zhe Li, Liang Zhao +3
Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the lar…
Towards Ultra-High Performance and Energy Efficiency of Deep Learning Systems: An Algorithm-Hardware Co-Optimization Framework
Yanzhi Wang, Caiwen Ding, Zhe Li +8
Hardware accelerations of deep learning systems have been extensively investigated in industry and academia. The aim of this paper is to achieve ultra-high energy efficiency and pe…
CirCNN: Accelerating and Compressing Deep Neural Networks Using Block-CirculantWeight Matrices
Caiwen Ding, Siyu Liao, Yanzhi Wang +13
Large-scale deep neural networks (DNNs) are both compute and memory intensive. As the size of DNNs continues to grow, it is critical to improve the energy efficiency and performanc…
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
Liang Zhao, Siyu Liao, Yanzhi Wang +4
Recently low displacement rank (LDR) matrices, or so-called structured matrices, have been proposed to compress large-scale neural networks. Empirical results have shown that neura…