Model compression and hardware acceleration for neural networks: A comprehensive survey

L Deng, G Li, S Han, L Shi, Y ** and magnitude-aware differentiation for improved quantization-aware training
C Sakr, S Dai, R Venkatesan… - International …, 2022 - proceedings.mlr.press
Data clip** is crucial in reducing noise in quantization operations and improving the
achievable accuracy of quantization-aware training (QAT). Current practices rely on …

Deep k-means: Re-training and parameter sharing with harder cluster assignments for compressing deep convolutions

J Wu, Y Wang, Z Wu, Z Wang… - International …, 2018 - proceedings.mlr.press
The current trend of pushing CNNs deeper with convolutions has created a pressing
demand to achieve higher compression gains on CNNs where convolutions dominate the …