PyTorch Legendre Memory Unit
Implementation of the Legendre Memory Unit in PyTorch. Ported from this repo and based on this paper presented at NeurIPS 2019.
TODO
- Example usage
- Reproduce results from the original paper
- Optimized
LMU
implementation to replace looping of anLMUCell
Citation
@inproceedings{voelker2019lmu,
title={Legendre Memory Units: Continuous-Time Representation in Recurrent Neural Networks},
author={Aaron R. Voelker and Ivana Kaji\'c and Chris Eliasmith},
booktitle={Advances in Neural Information Processing Systems},
pages={15544--15553},
year={2019}
}