Deep Learning of Dynamics and Coordinates with SINDy Autoencoders

Explore a groundbreaking approach to discovering models and effective coordinate systems using a custom SINDy autoencoder in this 25-minute video presentation. Delve into the research conducted by Kathleen Champion and her colleagues, as published in PNAS. Learn about the challenges of high-dimensional data and how SINDy autoencoders can address them. Understand the training process and see a proof of concept demonstration. Gain insights into the potential applications of this innovative technique in the field of deep learning and dynamics. Access the related GitHub repository for further exploration and implementation.