Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Linear Approximation in Time Domain01:21

Linear Approximation in Time Domain

384
Nonlinear systems often require sophisticated approaches for accurate modeling and analysis, with state-space representation being particularly effective. This method is especially useful for systems where variables and parameters vary with time or operating conditions, such as in a simple pendulum or a translational mechanical system with nonlinear springs.
For a simple pendulum with a mass evenly distributed along its length and the center of mass located at half the pendulum's length,...
384
Sampling Continuous Time Signal01:11

Sampling Continuous Time Signal

783
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
783
Curvilinear Motion: Rectangular Components01:23

Curvilinear Motion: Rectangular Components

1.4K
Curvilinear motion characterizes the movement of a particle or object along a curved path, notably evident when envisioning a car navigating a winding road. If the car starts at point A, its position vector is established within a fixed frame of reference, where the ratio of the position vector to its magnitude signifies the unit vector pointing in the position vector's direction.
As the car advances, its position evolves over time. Quantifying the car's velocity involves computing the...
1.4K
Linear time-invariant Systems01:23

Linear time-invariant Systems

993
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...
993
Linear Approximation in Frequency Domain01:26

Linear Approximation in Frequency Domain

407
Linear systems are characterized by two main properties: superposition and homogeneity. Superposition allows the response to multiple inputs to be the sum of the responses to each individual input. Homogeneity ensures that scaling an input by a scalar results in the response being scaled by the same scalar.
In contrast, nonlinear systems do not inherently possess these properties. However, for small deviations around an operating point, a nonlinear system can often be approximated as linear....
407
Basic Continuous Time Signals01:22

Basic Continuous Time Signals

742
Basic continuous-time signals include the unit step function, unit impulse function, and unit ramp function, collectively referred to as singularity functions. Singularity functions are characterized by discontinuities or discontinuous derivatives.
The unit step function, denoted u(t), is zero for negative time values and one for positive time values, exhibiting a discontinuity at t=0. This function often represents abrupt changes, such as the step voltage introduced when turning a car's...
742

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

SigmaScheduling: Uncertainty-Informed Scheduling of Decision Points for Intelligent Mobile Health Interventions.

... International Conference on Wearable and Implantable Body Sensor Networks. International Conference on Wearable and Implantable Body Sensor Networks·2026
Same author

Multi-Time Attention Networks for Irregularly Sampled Time Series.

... International Conference on Learning Representations·2026
Same author

Dynamic Modeling and System Identification of User Engagement in mHealth Interventions using a Bayesian Approach for Missing Data Imputation.

Control engineering practice·2025
Same author

Understanding the Policy Space for AgeTech: Implications for AI and Digital Health.

The Public policy and aging report·2025
Same author

Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation.

Proceedings of machine learning research·2024
Same author

BayesLDM: A Domain-specific Modeling Language for Probabilistic Modeling of Longitudinal Data.

...IEEE...International Conference on Connected Health: Applications, Systems and Engineering Technologies. IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies·2023
Same journal

Continual Slow-and-Fast Adaptation of Latent Neural Dynamics (CoSFan): Meta-Learning What-How & When to Adapt.

... International Conference on Learning Representations·2026
Same journal

Topology-Aware Segmentation Using Discrete Morse Theory.

... International Conference on Learning Representations·2026
Same journal

TOPODIFFUSIONNET: A TOPOLOGY-AWARE DIFFUSION MODEL.

... International Conference on Learning Representations·2026
Same journal

GEOMETRY OF LONG-TAILED REPRESENTATION LEARNING: REBALANCING FEATURES FOR SKEWED DISTRIBUTIONS.

... International Conference on Learning Representations·2026
Same journal

Probabilistic Geometric Principal Component Analysis with application to neural data.

... International Conference on Learning Representations·2026
Same journal

BRAID: Input-driven nonlinear dynamical modeling of neural-behavioral data.

... International Conference on Learning Representations·2026
See all related articles

Related Experiment Video

Updated: Feb 26, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.7K

Heteroscedastic Temporal Variational Autoencoder for Irregular Time Series.

Satya Narayan Shukla1, Benjamin M Marlin1

  • 1College of Information and Computer Sciences, University of Massachusetts Amherst, Amherst, MA 01003, USA.

... International Conference on Learning Representations
|February 25, 2026
PubMed
Summary
This summary is machine-generated.

We introduce the Heteroscedastic Temporal Variational Autoencoder (HeTVAE), a deep learning framework for interpolating irregularly sampled time series. HeTVAE effectively models and reflects temporal uncertainty caused by sparse data.

Related Experiment Videos

Last Updated: Feb 26, 2026

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines
08:27

Author Spotlight: Efficient Image Recognition Using Directional Gradient Histogram Technique and Support Vector Machines

Published on: January 5, 2024

1.7K

Area of Science:

  • Machine Learning
  • Time Series Analysis
  • Deep Learning

Background:

  • Irregularly sampled time series pose challenges for standard deep learning models.
  • Accurate interpolation and uncertainty quantification are crucial in domains with sparse data.

Purpose of the Study:

  • To develop a novel deep learning framework for probabilistic interpolation of irregularly sampled time series.
  • To improve the modeling of uncertainty in time series data with irregular sampling patterns.

Main Methods:

  • Proposed the Heteroscedastic Temporal Variational Autoencoder (HeTVAE) framework.
  • Introduced a novel input layer to encode observation sparsity.
  • Utilized a temporal Variational Autoencoder (VAE) architecture to propagate uncertainty.
  • Incorporated a heteroscedastic output layer for variable uncertainty in interpolations.

Main Results:

  • HeTVAE demonstrated superior performance in reflecting variable uncertainty over time compared to baseline and traditional models.
  • The proposed architecture outperformed recent deep latent variable models with homoscedastic output layers.
  • HeTVAE effectively handled uncertainty arising from sparse and irregular time series sampling.

Conclusions:

  • The Heteroscedastic Temporal Variational Autoencoder (HeTVAE) provides an effective solution for probabilistic interpolation of irregularly sampled time series.
  • HeTVAE's ability to model heteroscedastic uncertainty is key to its improved performance in sparse data scenarios.
  • This framework offers a significant advancement for deep learning applications dealing with real-world, irregularly sampled temporal data.