1 code implementation • 11 Apr 2022 • Ryan Vogt, Yang Zheng, Eli Shlizerman
To address the fact that RNN features go beyond the existing Lyapunov spectral analysis, we propose to infer relevant features from the Lyapunov spectrum with an Autoencoder and an embedding of its latent representation (AeLLE).
no code implementations • 7 Dec 2020 • N. Anders Petersson, Fortino Garcia, Daniel E. A. Appelo, Stefanie Guenther, Younsoo Choi, Ryan Vogt
This report explains the basic theory and common terminology of quantum physics without assuming any knowledge of physics.
Quantum Physics Mathematical Physics Mathematical Physics 65-00, 81-00
no code implementations • 25 Jun 2020 • Ryan Vogt, Maximilian Puelma Touzel, Eli Shlizerman, Guillaume Lajoie
Recurrent neural networks (RNNs) have been successfully applied to a variety of problems involving sequential data, but their optimization is sensitive to parameter initialization, architecture, and optimizer hyperparameters.