Patent for Reducing AI Model Size and Energy Consumption
ECE Professor Yanzhi Wang and Associate Professor Xue “Shelley” Lin were awarded a patent for “Computer-implemented methods and systems for compressing deep neural network models using alternating direction method of multipliers (ADMM).”
Abstract Source: USPTO
ADMM-NN is an algorithm-hardware co-optimization framework of DNNs using Alternating Direction Method of Multipliers (ADMM). The first part of ADMM-NN is a systematic, joint framework of DNN weight pruning and quantization using ADMM. The second part is a hardware-aware optimization to facilitate hardware-level implementations. ADMM-based weight pruning and quantization accounts for (i) computation reduction and energy efficiency improvement and (ii) performance overhead due to irregular sparsity. Experimental results demonstrate that by combining weight pruning and quantization, the proposed framework can achieve 1,910× and 231× reductions in the overall model size on the LeNet-5 and AlexNet models. Favorable results are also observed on VGGNet and ResNet models. Also, without any accuracy loss, 3.6× reduction in the amount of computation can be achieved, outperforming prior work.
