Search Results for author:
Found 7 papers, 4 papers with code
Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
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.
Chaotic Regularization and Heavy-Tailed Limits for Deterministic Gradient Descent
Recent studies have shown that gradient descent (GD) can achieve improved generalization when its dynamics exhibits a chaotic behavior.
NoisyMix: Boosting Model Robustness to Common Corruptions
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.
Noisy Feature Mixup
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.
Noisy Recurrent Neural Networks
We provide a general framework for studying recurrent neural networks (RNNs) trained by injecting noise into hidden states.
Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory
This representation is interpretable and disentangles the input signal from the SRNN architecture.
Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing
We study the problem of predicting rare critical transition events for a class of slow-fast nonlinear dynamical systems.
