Recurrent Neural Processes
arXiv:1906.05915
Abstract
We extend Neural Processes (NPs) to sequential data through Recurrent NPs or RNPs, a family of conditional state space models. RNPs model the state space with Neural Processes. Given time series observed on fast real-world time scales but containing slow long-term variabilities, RNPs may derive appropriate slow latent time scales. They do so in an efficient manner by establishing conditional independence among subsequences of the time series. Our theoretically grounded framework for stochastic processes expands the applicability of NPs while retaining their benefits of flexibility, uncertainty estimation, and favorable runtime with respect to Gaussian Processes (GPs). We demonstrate that state spaces learned by RNPs benefit predictive performance on real-world time-series data and nonlinear system identification, even in the case of limited data availability.
References in corpus (8)
- A Clockwork RNN
- Composing graphical models with neural networks for structured representations and fast inference
- Learning Stochastic Recurrent Networks
- Towards a Neural Statistician
- Sequential Neural Processes
- Meta-learning of Sequential Strategies
- Predictive State Recurrent Neural Networks
- Predictive-State Decoders: Encoding the Future into Recurrent Networks
Cited by in corpus (8)
- Artificial Neural Networks for Photonic Applications: From Algorithms to Implementation
- Few-shot Learning for Time-series Forecasting
- Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process
- Bootstrapping Neural Processes
- Few-Shot Learning Patterns in Financial Time-Series for Trend-Following Strategies
- GP-ConvCNP: Better Generalization for Convolutional Conditional Neural Processes on Time Series Data
- Meta-Learning for Koopman Spectral Analysis with Short Time-series
- Robustifying Sequential Neural Processes