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

Multi-input and Multi-variable systems01:22

Multi-input and Multi-variable systems

84
Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence...
84
Propagation of Uncertainty from Random Error00:59

Propagation of Uncertainty from Random Error

487
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...
487
Associative Learning01:27

Associative Learning

234
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
234
Improving Translational Accuracy02:07

Improving Translational Accuracy

2.5K
2.5K
Propagation of Uncertainty from Systematic Error01:10

Propagation of Uncertainty from Systematic Error

333
The atomic mass of an element varies due to the relative ratio of its isotopes. A sample's relative proportion of oxygen isotopes influences its average atomic mass. For instance, if we were to measure the atomic mass of oxygen from a sample, the mass would be a weighted average of the isotopic masses of oxygen in that sample. Since a single sample is not likely to perfectly reflect the true atomic mass of oxygen for all the molecules of oxygen on Earth, the mass we obtain from this...
333
Residuals and Least-Squares Property01:11

Residuals and Least-Squares Property

7.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.2K

You might also read

Related Articles

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

Sort by
Same author

Hypomagnetic Field Enhances U2OS Cell Proliferation and Migration by Promoting β-Catenin Phosphorylation and Upregulating FN1 and LOX Expression.

Cells·2026
Same author

VAMP8 function reveals tight linkage between endocytic recycling and endocytosis.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

A bacterial YopJ-family acetyltransferase suppresses host immune response by Nε-acetylation of JAK1.

Nature communications·2026
Same author

Environmental antibiotics in wastewater disrupt zebrafish embryonic development via Wnt/β-catenin signaling: mechanistic insights and implications for risk assessment.

Ecotoxicology and environmental safety·2026
Same author

Genetic Control of Tissue Remodeling by a Non-Coding SNP in ITGA8 Explains Carotenoid-Based Color Polymorphism in Marine Mollusks.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2026
Same author

The KANSL1-ARL17A fusion gene generates oncogenic chKANSARL and F-circKA RNAs that synergistically drive lung cancer progression via a novel F-circKA/miR-6860/chKANSARL axis.

The Journal of biological chemistry·2026
Same journal

Hidden Data Recovery and Forecasting via Next-Generation Reservoir Computing With Multiscale Delay Selection.

IEEE transactions on neural networks and learning systems·2026
Same journal

CAFF-CIL: Causality-Aware Freedom Forgetting Approach for Class-Incremental Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Harmonic Autoencoding Framework for Multiple Tasks in Magnetic Particle Imaging Reconstruction.

IEEE transactions on neural networks and learning systems·2026
Same journal

A Survey on Human-Centric Voice-Face Multimodal Learning.

IEEE transactions on neural networks and learning systems·2026
Same journal

Vision-Assisted Foundation Model for Solving Multitask Vehicle Routing Problems.

IEEE transactions on neural networks and learning systems·2026
Same journal

FP3O: Enabling Proximal Policy Optimization in Multiagent Cooperation With Parameter-Sharing Versatility.

IEEE transactions on neural networks and learning systems·2026
See all related articles

Related Experiment Video

Updated: May 9, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

426

AdvMixUp: Adversarial MixUp Regularization for Deep Learning.

Jun Fu, Xianrui Ji, Dexiong Chen

    IEEE Transactions on Neural Networks and Learning Systems
    |May 6, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Adversarial MixUp (AdvMixUp) enhances deep neural networks by generating challenging virtual samples, reducing overfitting. This novel method improves model robustness and performance compared to existing techniques.

    More Related Videos

    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K
    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

    458

    Related Experiment Videos

    Last Updated: May 9, 2025

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
    03:31

    Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

    Published on: December 15, 2023

    426
    Deep Neural Networks for Image-Based Dietary Assessment
    13:19

    Deep Neural Networks for Image-Based Dietary Assessment

    Published on: March 13, 2021

    8.9K
    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

    458

    Area of Science:

    • Computer Science
    • Artificial Intelligence
    • Machine Learning

    Background:

    • Deep neural networks (DNNs) achieve high performance but are prone to overfitting.
    • Existing data augmentation methods like MixUp struggle to generate effective samples near decision boundaries.

    Purpose of the Study:

    • To introduce Adversarial MixUp (AdvMixUp), a novel regularization technique for DNNs.
    • To improve the generation of challenging mixed samples for better model optimization.

    Main Methods:

    • AdvMixUp integrates adversarial training (AT) with MixUp.
    • It creates sample-dependent, feature-level interpolation masks for virtual sample generation.
    • These virtual samples are designed to be harder, pushing the model's decision boundaries.

    Main Results:

    • AdvMixUp successfully generates more challenging mixed samples compared to standard MixUp.
    • The method leads to more robust feature learning in DNNs.
    • Empirical results on CIFAR-10, CIFAR-100, Tiny-ImageNet, and ImageNet show AdvMixUp outperforms existing variants.

    Conclusions:

    • AdvMixUp is an effective method for regularizing DNNs and mitigating overfitting.
    • The technique enhances model robustness by creating informative, adversarial samples.
    • AdvMixUp offers a promising advancement in data augmentation for deep learning.