Fetching the paper…
Reading the bibliography…
Kronecker Products (KP) have been used to compress IoT RNN Applications by 15-38x compression factors, achieving better results than traditional compression methods.
Compression of recurrent neural networks for efficient language modeling
Grachev, A. M., Ignatov, D. I., and Savchenko, A. V · 1902
Earlier work this paper cites.
Measuring scheduling efficiency of rnns for NLP applications
Thakker, U., Dasika, G., Beu, J. G., and Mattina, M · 1904
Earlier work this paper cites.
Run-time efficient RNN compression for inference on edge devices
Thakker, U., Beu, J. G., Gope, D., Dasika, G., and Mattina, M · 1906
Earlier work this paper cites.
Compressing rnns for iot devices by 15-38x using kronecker products
Thakker, U., Beu, J. G., Gope, D., Zhou, C., Fedorov, I., Dasika, G., and Mattina, M · 1906
Earlier work this paper cites.
Pushing the limits of RNN compression
Thakker, U., Fedorov, I., Beu, J. G., Gope, D., Zhou, C., Dasika, G., and Mattina, M · 1910
Earlier work this paper cites.
To prune, or not to prune: exploring the efficacy of pruning for model compression
Zhu, M. and Gupta, S · 2001
Earlier work this paper cites.
Recurrent neural network regularization
Zaremba, W., Sutskever, I., and Vinyals, O · 2014
Earlier work this paper cites.
Structured transforms for small-footprint deep learning
Sindhwani, V., Sainath, T., and Kumar, S · 2015
Cited alongside, same era.
Binarynet: Training deep neural networks with weights and activations constrained to +1 or -1
Courbariaux, M. and Bengio, Y · 2016
Cited alongside, same era.
Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding
Han, S., Mao, H., and Dally, W. J · 2016
Cited alongside, same era.
Deep networks with stochastic depth
Huang, G., Sun, Y., Liu, Z., Sedra, D., and Weinberger, K. Q · 2016
Cited alongside, same era.
Quantized neural networks: Training neural networks with low precision weights and activations
Hubara, I., Courbariaux, M., Soudry, D., El-Yaniv, R., and Bengio, Y · 2016
Weighted-entropy-based quantization for deep neural networks
Park, E., Ahn, J., and Yoo, S · 2017
Later among the works it cites.
Compressing recurrent neural network with tensor train
Tjandra, A., Sakti, S., and Nakamura, S · 2017
Later among the works it cites.
Retraining-based iterative weight quantization for deep neural networks
Lee, D. and Kim, B · 2018
Later among the works it cites.
Deeptwist: Learning model compression via occasional weight distortion
Lee, D., Kapoor, P., and Kim, B · 2018
Later among the works it cites.
Ternary hybrid neural-tree networks for highly constrained iot applications
Gope, D., Dasika, G., and Mattina, M · 2019
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
Cited alongside, same era.
Factorization tricks for LSTM networks
Kuchaiev, O. and Ginsburg, B · 2017
Cited alongside, same era.
Ternary mobilenets via per-layer hybrid filter banks
Gope, D., Beu, J., Thakker, U., and Mattina, M
Cited in the paper.
Aggressive compression of mobilenets using hybrid ternary layers
Gope, D., Beu, J. G., Thakker, U., and Mattina, M
Cited in the paper.
Tao, J., Thakker, U., Dasika, G., and Beu, J · 2019
Later among the works it cites.