This code base if for a SHallow REcurrent Decoder (SHRED) machine learning architecture which featueres a sequence model (RNN, LSTM, etc) whose latent space is pushed through a shallor decoder network mapping back to the high-dimensional state space.

The SHRED method was first proposed and developed in this paper:

J. Williams, O. Zahn and J. N. Kutz, Sensing with shallow recurrent decoder networks, arxiv (2023) arXiv:2301.12011

The original code base is here: https://github.com/Jan-Williams/pyshred