DeepAI AI Chat
Log In Sign Up

Time Dependence in Non-Autonomous Neural ODEs

by   Jared Quincy Davis, et al.

Neural Ordinary Differential Equations (ODEs) are elegant reinterpretations of deep networks where continuous time can replace the discrete notion of depth, ODE solvers perform forward propagation, and the adjoint method enables efficient, constant memory backpropagation. Neural ODEs are universal approximators only when they are non-autonomous, that is, the dynamics depends explicitly on time. We propose a novel family of Neural ODEs with time-varying weights, where time-dependence is non-parametric, and the smoothness of weight trajectories can be explicitly controlled to allow a tradeoff between expressiveness and efficiency. Using this enhanced expressiveness, we outperform previous Neural ODE variants in both speed and representational capacity, ultimately outperforming standard ResNet and CNN models on select image classification and video prediction tasks.


Generalization bounds for neural ordinary differential equations and deep residual networks

Neural ordinary differential equations (neural ODEs) are a popular famil...

Neural Controlled Differential Equations for Online Prediction Tasks

Neural controlled differential equations (Neural CDEs) are a continuous-...

Neural Ordinary Differential Equations

We introduce a new family of deep neural network models. Instead of spec...

Delay Differential Neural Networks

Neural ordinary differential equations (NODEs) treat computation of inte...

A Neural RDE approach for continuous-time non-Markovian stochastic control problems

We propose a novel framework for solving continuous-time non-Markovian s...

Neural Differential Equations for Learning to Program Neural Nets Through Continuous Learning Rules

Neural ordinary differential equations (ODEs) have attracted much attent...

PAC bounds of continuous Linear Parameter-Varying systems related to neural ODEs

We consider the problem of learning Neural Ordinary Differential Equatio...