📈 Adaptive: parallel active learning of mathematical functions

RWKV (pronounced RwaKuv) is an RNN with great LLM performance, which can also be directly trained like a GPT transformer (parallelizable). We are at RWKV-7 "Goose". So it's combining the best of RN…

A package for computing data-driven approximations to the Koopman operator.

Linear and non-linear spectral forecasting algorithms

Manipulate audio with a simple and easy high level interface