Keywords: RNNs, Oscillators, Gradient stability, Long-term dependencies
Abstract: Circuits of biological neurons, such as in the functional parts of the brain can be modeled as networks of coupled oscillators. Inspired by the ability of these systems to express a rich set of outputs while keeping (gradients of) state variables bounded, we propose a novel architecture for recurrent neural networks. Our proposed RNN is based on a time-discretization of a system of second-order ordinary differential equations, modeling networks of controlled nonlinear oscillators. We prove precise bounds on the gradients of the hidden states, leading to the mitigation of the exploding and vanishing gradient problem for this RNN. Experiments show that the proposed RNN is comparable in performance to the state of the art on a variety of benchmarks, demonstrating the potential of this architecture to provide stable and accurate RNNs for processing complex sequential data.
One-sentence Summary: A biologically motivated and discretized ODE based RNN for learning long-term dependencies, with rigorous bounds mitigating the exploding and vanishing gradient problem.
Supplementary Material: zip
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Code: [![github](/images/github_icon.svg) tk-rusch/coRNN](https://github.com/tk-rusch/coRNN)
Data: [CIFAR-10](https://paperswithcode.com/dataset/cifar-10), [IMDb Movie Reviews](https://paperswithcode.com/dataset/imdb-movie-reviews), [MNIST](https://paperswithcode.com/dataset/mnist)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:2010.00951/code)