Time series forecasting is the task of predicting future values of a time series (as well as uncertainty bounds).
We introduce Gluon Time Series (GluonTS, available at https://gluon-ts. mxnet. io), a library for deep-learning-based time series modeling.
SOTA for Time Series on Bitcoin-Alpha
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
#3 best model for Traffic Prediction on PeMS-M
Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation.
To obtain accurate prediction, it is crucial to model long-term dependency in time series data, which can be achieved to some good extent by recurrent neural network (RNN) with attention mechanism.
Inspired by Memory Network proposed for solving the question-answering task, we propose a deep learning based model named Memory Time-series network (MTNet) for time series forecasting.
The explosion of time series data in recent years has brought a flourish of new time series analysis methods, for forecasting, clustering, classification and other tasks.
Natural spatiotemporal processes can be highly non-stationary in many ways, e. g. the low-level non-stationarity such as spatial correlations or temporal dependencies of local pixel values; and the high-level variations such as the accumulation, deformation or dissipation of radar echoes in precipitation forecasting.
SOTA for Video Prediction on Human3.6M
We introduce a differentiable loss function suitable for training deep neural nets, and provide a custom back-prop implementation for speeding up optimization.