Code for paper "Tuneable Efficient Unitary Neural Networks (EUNN) and their application to RNns." Based on the urnn repository from https://github.com/stwisdom/urnn.
Code coming soon for other experiments.
If you find this code useful, please cite the following references:
[1] M. Arjovsky, A. Shah, and Y. Bengio, “Unitary Evolution Recurrent Neural Networks,” Proc. International Conference on Machine Learning (ICML), 2016, pp. 1120–1128.
[2] S. Wisdom, T. Powers, J.R. Hershey, J. Le Roux, and L. Atlas, "Full-Capacity Unitary Recurrent Neural Networks," Advances in Neural Information Processing Systems (NIPS), 2016.
[3] L. Jing, Y. Shen, T. Dubcek, J. Peurifoy, S. Skirlo, Y. LeCun, M. Tegmark, M. Soljacic, "Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs", Arxiv 2017