Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mikhaeil, Jonas M."'
Autor:
Brenner, Manuel, Hess, Florian, Mikhaeil, Jonas M., Bereska, Leonard, Monfared, Zahra, Kuo, Po-Chen, Durstewitz, Daniel
In many scientific disciplines, we are interested in inferring the nonlinear dynamical system underlying a set of observed time series, a challenging task in the face of chaotic behavior and noise. Previous deep learning approaches toward this goal o
Externí odkaz:
http://arxiv.org/abs/2207.02542
Recurrent neural networks (RNNs) are wide-spread machine learning tools for modeling sequential and time series data. They are notoriously hard to train because their loss gradients backpropagated in time tend to saturate or diverge during training.
Externí odkaz:
http://arxiv.org/abs/2110.07238