Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time 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.

References in corpus (9)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• On the difficulty of training Recurrent Neural Networks
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Hamiltonian Neural Networks
• Full-Capacity Unitary Recurrent Neural Networks
• Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
• AntisymmetricRNN: A Dynamical System View on Recurrent Neural Networks
• Lipschitz Recurrent Neural Networks
• A recurrent neural network without chaos

Cited by in corpus (4)

• FlexConv: Continuous Kernel Convolutions with Differentiable Kernel Sizes
• Slower is Better: Revisiting the Forgetting Mechanism in LSTM for Slower Information Decay
• Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory
• DeepSITH: Efficient Learning via Decomposition of What and When Across Time Scales