The goal of Time Series Prediction is to infer the future values of a time series from the past.
In this study, we develop a novel method, Dynamic Virtual Graph Significance Networks (DVGSN), which can supervisedly and dynamically learn from similar "infection situations" in historical timepoints.
It makes fundamental improvements over the mainstream temporal convolutional neural networks, including the incorporation of separable depth-wise convolution to reduce the computational complexity of the model and residual connections as time attention machines, increase the network depth and accuracy.
We introduce deep switching auto-regressive factorization (DSARF), a deep generative model for spatio-temporal data with the capability to unravel recurring patterns in the data and perform robust short- and long-term predictions.
We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks.
Ranked #1 on Traffic Prediction on PeMS04
Existing asymmetric multi-task learning methods tackle this negative transfer problem by performing knowledge transfer from tasks with low loss to tasks with high loss.
In this paper, we propose a low-rank autoregressive tensor completion (LATC) framework to model multivariate time series data.
Reservoir Computing is a class of simple yet efficient Recurrent Neural Networks where internal weights are fixed at random and only a linear output layer is trained.
Understanding human motion behaviour is a critical task for several possible applications like self-driving cars or social robots, and in general for all those settings where an autonomous agent has to navigate inside a human-centric environment.
Ranked #1 on Trajectory Prediction on STATS SportVu NBA [ATK]