Neural Integro-Differential Equations

by   Emanuele Zappala, et al.

Modeling continuous dynamical systems from discretely sampled observations is a fundamental problem in data science. Often, such dynamics are the result of non-local processes that present an integral over time. As such, these systems are modeled with Integro-Differential Equations (IDEs); generalizations of differential equations that comprise both an integral and a differential component. For example, brain dynamics are not accurately modeled by differential equations since their behavior is non-Markovian, i.e. dynamics are in part dictated by history. Here, we introduce the Neural IDE (NIDE), a framework that models ordinary and integral components of IDEs using neural networks. We test NIDE on several toy and brain activity datasets and demonstrate that NIDE outperforms other models, including Neural ODE. These tasks include time extrapolation as well as predicting dynamics from unseen initial conditions, which we test on whole-cortex activity recordings in freely behaving mice. Further, we show that NIDE can decompose dynamics into its Markovian and non-Markovian constituents, via the learned integral operator, which we test on fMRI brain activity recordings of people on ketamine. Finally, the integrand of the integral operator provides a latent space that gives insight into the underlying dynamics, which we demonstrate on wide-field brain imaging recordings. Altogether, NIDE is a novel approach that enables modeling of complex non-local dynamics with neural networks.


page 1

page 2

page 3

page 4


Neural Integral Equations

Integral equations (IEs) are functional equations defined through integr...

GOKU-UI: Ubiquitous Inference through Attention and Multiple Shooting for Continuous-time Generative Models

Scientific Machine Learning (SciML) is a burgeoning field that synergist...

Neural Piecewise-Constant Delay Differential Equations

Continuous-depth neural networks, such as the Neural Ordinary Differenti...

Semi-linear Poisson-mediated Flocking in a Cucker-Smale Model

We propose a family of compactly supported parametric interaction functi...

Learning low-dimensional dynamics from whole-brain data improves task capture

The neural dynamics underlying brain activity are critical to understand...

Model Checking for Parametric Ordinary Differential Equations System

Ordinary differential equations have been used to model dynamical system...

Learning Nonlinear Brain Dynamics: van der Pol Meets LSTM

Many real-world data sets, especially in biology, are produced by highly...

Please sign up or login with your details

Forgot password? Click here to reset