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

Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

569
Accuracy, limits, and approximations are common in many fields, especially in engineering calculations. These concepts are imperative for ensuring that a given value is as close as possible to its true value.
Accuracy is defined as the closeness of the measured value to the true or actual value. In engineering mechanics, repeated measurements are taken during theoretical or experimental analyses to ensure that the result is precise and accurate.
The accuracy of any solution is based on the...
569
Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K
Variance01:15

Variance

10.7K
 The deviations show how spread out the data are about the mean. A positive deviation occurs when the data value exceeds the mean, whereas a negative deviation occurs when the data value is less than the mean. If the deviations are added, the sum is always zero. So one cannot simply add the deviations to get the data spread. By squaring the deviations, the numbers are made positive; thus, their sum will also be positive.
The standard deviation measures the spread in the same units as the...
10.7K
Coefficient of Variation01:10

Coefficient of Variation

5.5K
The coefficient of variation measures the dispersion of the data points or distribution around the mean. Using the coefficient of variation, we can compare two data series with drastically different means or different units of measurement. The coefficient of variation for a sample and a population is expressed as a percentage of the ratio of standard deviation to the mean.
The coefficient of variation is a practical statistical tool in finance. It allows investors to assess the volatility or...
5.5K
Variability: Analysis01:11

Variability: Analysis

215
Measures of variability are statistical metrics that reveal the dispersion pattern within a dataset. They are pivotal in biostatistics, providing insights into the heterogeneity within health and biological data. Variability signifies the degree to which data points diverge from one another, helping researchers understand the potential range of values and associated uncertainty within the data.
The range is a simple measure of variability, indicating the difference between the highest and...
215
Propagation of Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

1.2K
An experiment often consists of more than a single step. In this case, measurements at each step give rise to uncertainty. Because the measurements occur in successive steps, the uncertainty in one step necessarily contributes to that in the subsequent step. As we perform statistical analysis on these types of experiments, we must learn to account for the propagation of uncertainty from one step to the next. The propagation of uncertainty depends on the type of arithmetic operation performed on...
1.2K

You might also read

Related Articles

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

Sort by
Same author

Opinion dynamics in financial markets via random networks.

Proceedings of the National Academy of Sciences of the United States of America·2022
Same author

Investigation of Interfacial Layer for Ultrasonic Spot Welded Aluminum to Copper Joints.

Scientific reports·2017
Same author

Multiregional Sequencing Reveals Genomic Alterations and Clonal Dynamics in Primary Malignant Melanoma of the Esophagus.

Cancer research·2017
Same author

Integrated Analysis Reveals Tubal- and Ovarian-Originated Serous Ovarian Cancer and Predicts Differential Therapeutic Responses.

Clinical cancer research : an official journal of the American Association for Cancer Research·2017
Same author

Inverse Association between Ambient Sulfur Dioxide Exposure and Semen Quality in Wuhan, China.

Environmental science & technology·2017
Same author

Bacterial and Archaeal Lipids Recovered from Subsurface Evaporites of Dalangtan Playa on the Tibetan Plateau and Their Astrobiological Implications.

Astrobiology·2017

Related Experiment Video

Updated: Sep 29, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K

Coupled VAE: Improved Accuracy and Robustness of a Variational Autoencoder.

Shichen Cao1, Jingjing Li2, Kenric P Nelson3

  • 1Worcester Polytechnic Institute, Worcester, MA 01609, USA.

Entropy (Basel, Switzerland)
|March 25, 2022
PubMed
Summary

A new coupled variational autoencoder (VAE) method enhances handwritten numeral image representation accuracy and robustness. This approach improves image reconstruction likelihood and reduces latent distribution divergence, outperforming traditional VAEs, especially with corrupted data.

Keywords:
complex systemsentropymachine learningrobustnessstatistical mechanics

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

703
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

1.3K

Related Experiment Videos

Last Updated: Sep 29, 2025

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.3K
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

703
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

1.3K

Area of Science:

  • Machine Learning
  • Computer Vision
  • Statistical Modeling

Background:

  • Variational Autoencoders (VAEs) are powerful generative models but can struggle with noisy or outlier data.
  • Existing VAE variants, like beta-VAE, often involve trade-offs between reconstruction quality and latent space representation.
  • Accurate and robust representation of complex data, such as handwritten digits, remains a challenge.

Purpose of the Study:

  • To introduce a novel coupled variational autoencoder (VAE) method for improved handwritten numeral image representation.
  • To enhance model accuracy and robustness by addressing outlier samples and latent distribution divergence.
  • To demonstrate the superiority of the coupled VAE over existing methods, particularly in scenarios with corrupted input data.

Main Methods:

  • Developed a coupled variational autoencoder (VAE) by generalizing the evidence lower bound function with a coupled entropy function.
  • Incorporated principles of nonlinear statistical coupling to assign higher penalties to outlier samples.
  • Evaluated the model's performance on the Modified National Institute of Standards and Technology (MNIST) dataset and its corrupted version (C-MNIST).

Main Results:

  • The coupled VAE demonstrated significant improvements in image reconstruction likelihood compared to standard VAEs.
  • Performance gains were more substantial when the model was trained or tested with corrupted images (e.g., Gaussian corruption).
  • Reduced divergence between posterior and prior latent distributions, indicating a more stable and meaningful latent space representation.

Conclusions:

  • The coupled VAE method effectively enhances the accuracy and robustness of handwritten numeral image representation.
  • This approach successfully improves reconstruction quality and latent space properties without the typical trade-offs seen in other VAE designs.
  • The coupled VAE offers a promising advancement for generative modeling tasks involving imperfect or noisy data.