research
∙
07/04/2023
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Convolutional residual neural networks (ConvResNets), though overparamet...
share
research
∙
06/13/2022
Why Quantization Improves Generalization: NTK of Binary Weight Neural Networks
Quantized neural networks have drawn a lot of attention as they reduce t...
research
∙
04/20/2022
Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?
We study the theory of neural network (NN) from the lens of classical no...
research
∙
05/11/2021
3U-EdgeAI: Ultra-Low Memory Training, Ultra-Low BitwidthQuantization, and Ultra-Low Latency Acceleration
The deep neural network (DNN) based AI applications on the edge require ...
research
∙
04/07/2021
On-FPGA Training with Ultra Memory Reduction: A Low-Precision Tensor Method
Various hardware accelerators have been developed for energy-efficient a...
research
∙
10/20/2020
Sparse Tucker Tensor Decomposition on a Hybrid FPGA-CPU Platform
Recommendation systems, social network analysis, medical imaging, and da...
research
∙
10/29/2019
Active Subspace of Neural Networks: Structural Analysis and Universal Attacks
Active subspace is a model reduction method widely used in the uncertain...
research
∙
06/28/2019
Tucker Tensor Decomposition on FPGA
Tensor computation has emerged as a powerful mathematical tool for solvi...
research
∙
11/05/2018
A Unified Framework of DNN Weight Pruning and Weight Clustering/Quantization Using ADMM
Many model compression techniques of Deep Neural Networks (DNNs) have be...
research
∙
10/17/2018
Progressive Weight Pruning of Deep Neural Networks using ADMM
Deep neural networks (DNNs) although achieving human-level performance i...
research
∙
07/29/2018
ADAM-ADMM: A Unified, Systematic Framework of Structured Weight Pruning for DNNs
Weight pruning methods of deep neural networks (DNNs) have been demonstr...
research
∙
04/10/2018