A scalable end-to-end Gaussian process adapter for irregularly sampled time series classification

06/14/2016
by   Steven Cheng-Xian Li, et al.
0

We present a general framework for classification of sparse and irregularly-sampled time series. The properties of such time series can result in substantial uncertainty about the values of the underlying temporal processes, while making the data difficult to deal with using standard classification methods that assume fixed-dimensional feature spaces. To address these challenges, we propose an uncertainty-aware classification framework based on a special computational layer we refer to as the Gaussian process adapter that can connect irregularly sampled time series data to any black-box classifier learnable using gradient descent. We show how to scale up the required computations based on combining the structured kernel interpolation framework and the Lanczos approximation method, and how to discriminatively train the Gaussian process adapter in combination with a number of classifiers end-to-end using backpropagation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/13/2017

Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier

We present a scalable end-to-end classifier that uses streaming physiolo...
research
07/09/2019

A Robust Two-Sample Test for Time Series data

We develop a general framework for hypothesis testing with time series d...
research
11/21/2016

Probabilistic structure discovery in time series data

Existing methods for structure discovery in time series data construct i...
research
07/02/2022

Scheduling Planting Time Through Developing an Optimization Model and Analysis of Time Series Growing Degree Units

Producing higher-quality crops within shortened breeding cycles ensures ...
research
10/31/2016

Analysis of Nonstationary Time Series Using Locally Coupled Gaussian Processes

The analysis of nonstationary time series is of great importance in many...
research
11/17/2022

Neural Inference of Gaussian Processes for Time Series Data of Quasars

The study of quasar light curves poses two problems: inference of the po...
research
06/02/2021

Inferring Black Hole Properties from Astronomical Multivariate Time Series with Bayesian Attentive Neural Processes

Among the most extreme objects in the Universe, active galactic nuclei (...

Please sign up or login with your details

Forgot password? Click here to reset