Gated Recurrent Neural Networks with Weighted Time-Delay Feedback
Erichson, N. Benjamin, Lim, Soon Hoe, Mahoney, Michael W.
–arXiv.org Artificial Intelligence
We introduce a novel gated recurrent unit (GRU) with a weighted time-delay feedback mechanism in order to improve the modeling of long-term dependencies in sequential data. This model is a discretized version of a continuous-time formulation of a recurrent unit, where the dynamics are governed by delay differential equations (DDEs). By considering a suitable time-discretization scheme, we propose $\tau$-GRU, a discrete-time gated recurrent unit with delay. 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. Our empirical results show that $\tau$-GRU can converge faster and generalize better than state-of-the-art recurrent units and gated recurrent architectures on a range of tasks, including time-series classification, human activity recognition, and speech recognition.
arXiv.org Artificial Intelligence
Nov-30-2022
- Country:
- Pacific Ocean (0.04)
- North America > United States
- New York (0.04)
- Europe > Sweden
- Genre:
- Research Report > New Finding (0.34)
- Industry:
- Health & Medicine (0.46)
- Technology: