Closed-form Continuous-time Neural Models · HackerPapers discussions

Closed-form Continuous-time Neural Models — mentioned by programjames

Mon, 30 Sep 2024 16:49:19 GMT

The ideas come from these papers: 1. [Liquid Time-Constant Networks (2020)](https://arxiv.org/abs/2006.04439) This is essentially a neural ODE applied to leaky integrate-and-fire. 2. [Closed-form Continuous-time (2022)](https://arxiv.org/abs/2106.13898) A closed-form approximation of the first.

Paper and discussion history. A mention is not an endorsement.

Closed-form Continuous-time Neural Models — mentioned by f_devd

Wed, 08 Feb 2023 19:07:23 GMT

Although the article is recent the paper from the article has been available on preprint/arxiv since June 2021[1], implementations for pytorch & tensorflow are also available[2] for those interested. [1]: https://arxiv.org/abs/2106.13898 [2]: https://github.com/raminmh/CfC

Paper and discussion history. A mention is not an endorsement.