Neural ode processes

A Norcliffe, C Bodnar, B Day, J Moss, P Li��- arXiv preprint arXiv�…, 2021 - arxiv.org
arXiv preprint arXiv:2103.12413, 2021arxiv.org
Neural Ordinary Differential Equations (NODEs) use a neural network to model the
instantaneous rate of change in the state of a system. However, despite their apparent
suitability for dynamics-governed time-series, NODEs present a few disadvantages. First,
they are unable to adapt to incoming data points, a fundamental requirement for real-time
applications imposed by the natural direction of time. Second, time series are often
composed of a sparse set of measurements that could be explained by many possible�…
Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent suitability for dynamics-governed time-series, NODEs present a few disadvantages. First, they are unable to adapt to incoming data points, a fundamental requirement for real-time applications imposed by the natural direction of time. Second, time series are often composed of a sparse set of measurements that could be explained by many possible underlying dynamics. NODEs do not capture this uncertainty. In contrast, Neural Processes (NPs) are a family of models providing uncertainty estimation and fast data adaptation but lack an explicit treatment of the flow of time. To address these problems, we introduce Neural ODE Processes (NDPs), a new class of stochastic processes determined by a distribution over Neural ODEs. By maintaining an adaptive data-dependent distribution over the underlying ODE, we show that our model can successfully capture the dynamics of low-dimensional systems from just a few data points. At the same time, we demonstrate that NDPs scale up to challenging high-dimensional time-series with unknown latent dynamics such as rotating MNIST digits.
arxiv.org