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 Experiment Video

Updated: Feb 6, 2026

High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition
05:11

High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition

Published on: June 27, 2025

680

Denoising Adversarial Autoencoders.

Antonia Creswell, Anil Anthony Bharath

    IEEE Transactions on Neural Networks and Learning Systems
    |August 22, 2018
    PubMed
    Summary
    This summary is machine-generated.

    Denoising adversarial autoencoders (AAEs) improve unsupervised learning by reconstructing corrupted data, leading to better representations for classification and sample synthesis.

    Related Concept Videos

    You might also read

    Related Articles

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

    Sort by
    Same author

    Language models, like humans, show content effects on reasoning tasks.

    PNAS nexus·2024
    Same author

    Automated Identification of Orthopedic Implants on Radiographs Using Deep Learning.

    Radiology. Artificial intelligence·2021
    Same author

    Efficient Source Camera Identification with Diversity-Enhanced Patch Selection and Deep Residual Prediction.

    Sensors (Basel, Switzerland)·2021
    Same author

    Artificial Intelligence (AI) and rheumatology: a potential partnership.

    Rheumatology (Oxford, England)·2019
    Same author

    Inverting the Generator of a Generative Adversarial Network.

    IEEE transactions on neural networks and learning systems·2018
    Same author

    Detection of axonal synapses in 3D two-photon images.

    PloS one·2017

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Deep Learning

    Background:

    • Unsupervised learning leverages unlabeled data for inference.
    • Autoencoders learn data representations by reconstructing input from a latent space.
    • Regularization techniques shape latent space distributions for improved representations.

    Purpose of the Study:

    • To introduce denoising adversarial autoencoders (AAEs) combining denoising and adversarial training.
    • To analyze the integration of denoising into AAE training and sampling.
    • To evaluate the impact of denoising on representation learning for classification and sample synthesis.

    Main Methods:

    • Developed denoising adversarial autoencoders (AAEs).
    • Incorporated a novel analysis for denoising in AAE training and sampling.

    More Related Videos

    Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin
    11:17

    Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin

    Published on: March 10, 2021

    6.8K

    Related Experiment Videos

    Last Updated: Feb 6, 2026

    High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition
    05:11

    High-precision Electromagnetic Flowmeter with Empty Pipe Detection via Complex Programmable Logic Device-based Waveform Recognition

    Published on: June 27, 2025

    680
    Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin
    11:17

    Stability and Structure of Bat Major Histocompatibility Complex Class I with Heterologous β2-Microglobulin

    Published on: March 10, 2021

    6.8K
  • Conducted experiments on representation learning for classification and sample synthesis.

    • Main Results:

    • Autoencoders trained with denoising criteria yield enhanced representation learning.
    • Denoising improves classification performance compared to standard autoencoders.
    • Synthesized samples are more consistent with input data when using denoising.

    Conclusions:

    • Denoising is a valuable technique for improving autoencoder-based representation learning.
    • AAEs offer a robust approach for leveraging unlabeled data in machine learning.
    • The proposed denoising method enhances both classification accuracy and generative capabilities.