no code implementations • 1 Dec 2022 • N. Benjamin Erichson, Soon Hoe Lim, Michael W. Mahoney
We prove the existence and uniqueness of solutions for the continuous-time model, and we demonstrate that the proposed feedback mechanism can help improve the modeling of long-term dependencies.
1 code implementation • 23 May 2022 • Soon Hoe Lim, Yijun Wan, Umut Şimşekli
Recent studies have shown that gradient descent (GD) can achieve improved generalization when its dynamics exhibits a chaotic behavior.
no code implementations • 2 Feb 2022 • N. Benjamin Erichson, Soon Hoe Lim, Winnie Xu, Francisco Utrera, Ziang Cao, Michael W. Mahoney
For many real-world applications, obtaining stable and robust statistical performance is more important than simply achieving state-of-the-art predictive test accuracy, and thus robustness of neural networks is an increasingly important topic.
2 code implementations • ICLR 2022 • Soon Hoe Lim, N. Benjamin Erichson, Francisco Utrera, Winnie Xu, Michael W. Mahoney
We introduce Noisy Feature Mixup (NFM), an inexpensive yet effective method for data augmentation that combines the best of interpolation based training and noise injection schemes.
1 code implementation • NeurIPS 2021 • Soon Hoe Lim, N. Benjamin Erichson, Liam Hodgkinson, Michael W. Mahoney
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states.
no code implementations • 19 Jun 2020 • Soon Hoe Lim
This representation is interpretable and disentangles the input signal from the SRNN architecture.
2 code implementations • 10 Aug 2019 • Soon Hoe Lim, Ludovico Theo Giorgini, Woosok Moon, J. S. Wettlaufer
We study the problem of predicting rare critical transition events for a class of slow-fast nonlinear dynamical systems.