no code implementations • 27 Apr 2023 • Saurabh Malani, Tom S. Bertalan, Tianqi Cui, Jose L. Avalos, Michael Betenbaugh, Ioannis G. Kevrekidis
Iterates of such neural-network models allow for learning from data sampled at arbitrary time points $\textit{without}$ data modification.
no code implementations • 27 Apr 2021 • Felix P. Kemeth, Tom Bertalan, Nikolaos Evangelou, Tianqi Cui, Saurabh Malani, Ioannis G. Kevrekidis
We present an approach, based on learning an intrinsic data manifold, for the initialization of the internal state values of LSTM recurrent neural networks, ensuring consistency with the initial observed input data.