|Trend||Dataset||Best Method||Paper title||Paper||Code||Compare|
Instead of specifying a discrete sequence of hidden layers, we parameterize the derivative of the hidden state using a neural network.
#2 best model for Multivariate Time Series Imputation on MuJoCo
Spatiotemporal forecasting has various applications in neuroscience, climate and transportation domain.
#2 best model for Traffic Prediction on PeMS-M
We introduce a unified algorithm to efficiently learn a broad class of linear and non-linear state space models, including variants where the emission and transition distributions are modeled by deep neural networks.
#4 best model for Multivariate Time Series Forecasting on USHCN-Daily
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.
Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs).
We propose a patient subtyping model that leverages the proposed T-LSTM in an auto-encoder to learn a powerful single representation for sequential records of patients, which are then used to cluster patients into clinical subtypes.
#2 best model for Multivariate Time Series Forecasting on MIMIC-III
First, we show that LSTMs outperform existing techniques to predict the next event of a running case and its timestamp.
Multivariate time series data in practical applications, such as health care, geoscience, and biology, are characterized by a variety of missing values.
#4 best model for Multivariate Time Series Imputation on MuJoCo
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.