IEEE Design and Test · 2021 · 12 citations · 4 references
ComputingComputer ScienceMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingNeural NetworksPattern RecognitionAccuracyNeural Language ModelsNeural Network QuantizationRecurrent Neural Networks
This article proposes a Fast and Compact Ternary LSTM (FaCTLSTM), which bridges the accuracy gap between the full-precision and quantized neural networks.
4
Klaus Greff, Rupesh K. Srivastava, Jan Koutník et al. · IEEE Transactions on Neural Networks and Learning Systems · 2016 · 6.8K citations · Full text
Alternating Multi-bit Quantization for Recurrent Neural Networks
Chen Xu, Jianqiang Yao, Zhouchen Lin et al. · arXiv (Cornell University) · 2018 · 51 citations · Full text
TOT-Net: An Endeavor Toward Optimizing Ternary Neural Networks
Najmeh Nazari, Mohammad Loni, Mostafa E. Salehi et al. · 2019 · 22 citations