Fitting Regularized Population Dynamics with Neural Differential Equations
Neural differential equations (neural DEs) are yet to see success in its application as interpretable autoencoders/descriptors, where they directly model a population of signals with the learned vector field. In this manuscript, we show that there is a threshold to which these models capture the dynamics of a population of signals produced under the same monitoring protocol. This threshold is computed by taking the derivative at each time point and analyzing the variance of its dynamics. In addition, we show that this can be tackled by projecting a highly-variant population to a lower dynamically variant space, where the model is able to capture dynamics, and similarly project the modelled signal back to the original space.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Optimizing differential equations to fit data and predict outcomes
Many scientific problems focus on observed patterns of change or on how to design a system to achieve particular dynamics. Those problems often require fitting differential equation models to target trajectories. Fitting…
New insights into population dynamics from the continuous McKendrick model
The article covers the continuous McKendrick model, which is key in epidemiology and population dynamics, developed by Anderson Gray McKendrick. It describes population age structure changes via birth and death rates as …
EpidemiologyFast fitting of neural ordinary differential equations by Bayesian neural gradient matching to infer ecological interactions from time series data
1. Inferring ecological interactions is hard because we often lack suitable parametric representations to portray them. Neural ordinary differential equations (NODEs) provide a way of estimating interactions nonparametri…
Time SeriesTime Series AnalysisUncertainty QuantificationBridging the gap between individual-based and continuum models of growing cell populations
Continuum models for the spatial dynamics of growing cell populations have been widely used to investigate the mechanisms underpinning tissue development and tumour invasion. These models consist of nonlinear partial dif…
Short and Long Range Population Dynamics of the Monarch
The monarch butterfly annually migrates from central Mexico to southern Canada. During recent decades, its population has been reduced due to human interaction with their habitat. We examine the effect of herbicide usage…