To model time series accurately is important within a wide range of fields. As the world is generally too complex to be modelled exactly, it is often meaningful to assess the probability of a dynamical system to be in a specific state. This paper presents the Delay-SDE-net, a neural network model based on stochastic delay differential equations (SDDEs). The use of SDDEs with multiple delays as modelling framework makes it a suitable model for time series with memory effects, as it includes memory through previous states of the system. The stochastic part of the Delay-SDE-net provides a basis for estimating uncertainty in modelling, and is split into two neural networks to account for aleatoric and epistemic uncertainty. The uncertainty is provided instantly, making the model suitable for applications where time is sparse. We derive the theoretical error of the Delay-SDE-net and analyze the convergence rate numerically. At comparisons with similar models, the Delay-SDE-net has consistently the best performance, both in predicting time series values and uncertainties.
翻译:准确模拟时间序列在一系列广泛的领域非常重要。 由于世界通常过于复杂,无法精确地进行模拟,因此评估动态系统在特定状态下的概率往往很有意义。 本文件介绍了根据随机延迟差异方程式(SDDEs)建立神经网络模型的延迟-SDE-net。使用具有多重延迟的SDDEs作为模拟框架,使它成为具有记忆效果的时间序列的适当模型,因为它包括通过系统先前状态的记忆。延迟-SDE-net的随机部分为估算模型不确定性提供了基础,并分成两个神经网络,以计算偏移和感知不确定性。这种不确定性立即提供,使模型适合时间稀少的应用。我们从理论上分析延迟-SDE-net的错误,并以数字方式分析聚合率。在与类似模型进行比较时,延迟-SDE-net在预测时间序列值和不确定性方面都保持了最佳性能。</s>