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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

779
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
779
Difference from Background: Limit of Detection01:05

Difference from Background: Limit of Detection

7.0K
The limit of detection (LOD) is the smallest amount of analyte that can be distinguished from the background noise. The LOD value corresponds to the concentration at which the analyte signal is three times larger than the standard deviation of the blank signal. Below this value, the analyte signal cannot be differentiated from the background noise. It is calculated by dividing the calibration slope by 3 times the standard deviation of the blank signals.
The LOD indicates the presence or absence...
7.0K
Second Uniqueness Theorem01:16

Second Uniqueness Theorem

1.1K
Consider a region consisting of several individual conductors with a definite charge density in the region between these conductors. The second uniqueness theorem states that if the total charge on each conductor and the charge density in the in-between region are known, then the electric field can be uniquely determined.
In contrast, consider that the electric field is non-unique and apply Gauss's law in divergence form in the region between the conductors and the integral form to the...
1.1K
Quantifying and Rejecting Outliers: The Grubbs Test01:02

Quantifying and Rejecting Outliers: The Grubbs Test

1.9K
Sometimes, a data set can have a recorded numerical observation that greatly  deviates from the rest of the data. Assuming that the data is normally distributed, a statistical method called the Grubbs test can be used to determine whether the observation is truly an outlier.  To perform a two-tailed Grubbs test, first, calculate the absolute difference between the outlier and the mean. Then, calculate the ratio between this difference and the standard deviation of the sample. This...
1.9K
Classification of Signals01:30

Classification of Signals

856
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
856
Sign Test for Nominal Data01:12

Sign Test for Nominal Data

150
The sign test is a nonparametric method used to evaluate hypotheses about the median of a single sample or to compare the medians of two related samples. The sign test is particularly useful when dealing with nominal data, which includes distinct categories without an inherent order, such as names, labels, and preferences. Nominal data restricts statistical analysis to evaluating population proportions rather than mean or median values that require continuous data.
For example, consider a...
150

You might also read

Related Articles

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

Sort by
Same author

Deployment Prior Injection for Run-Time Re-Biasable Object Detection.

IEEE transactions on pattern analysis and machine intelligence·2026
Same author

Evaluation of UNeXt for Automatic Bone Surface Segmentation on Ultrasound Imaging in Image-Guided Pediatric Surgery.

Bioengineering (Basel, Switzerland)·2025
Same author

Evaluating the generalizability of video-based assessment of intraoperative surgical skill in capsulorhexis.

International journal of computer assisted radiology and surgery·2025
Same author

CBCT Reconstruction Using Single X-Ray Projection With Cycle-Domain Geometry-Integrated Denoising Diffusion Probabilistic Models.

IEEE transactions on medical imaging·2025
Same author

Land Resources for Wind Energy Development Requires Regionalized Characterizations.

Environmental science & technology·2024
Same author

ReconFormer: Accelerated MRI Reconstruction Using Recurrent Transformer.

IEEE transactions on medical imaging·2023

Related Experiment Video

Updated: Sep 5, 2025

Novel Object Recognition and Object Location Behavioral Testing in Mice on a Budget
05:57

Novel Object Recognition and Object Location Behavioral Testing in Mice on a Budget

Published on: November 20, 2018

56.5K

Adversarially Robust One-Class Novelty Detection.

Shao-Yuan Lo, Poojan Oza, Vishal M Patel

    IEEE Transactions on Pattern Analysis and Machine Intelligence
    |July 11, 2022
    PubMed
    Summary

    One-class novelty detectors are vulnerable to adversarial attacks. A new method, Principal Latent Space (PrincipaLS), enhances robustness by purifying the latent space against such attacks.

    Area of Science:

    • Artificial Intelligence
    • Machine Learning
    • Computer Vision

    Background:

    • One-class novelty detectors identify if a query belongs to a known class.
    • Deep auto-encoder architectures are common but vulnerable to adversarial attacks.
    • Existing defenses for classification are ineffective for novelty detection.

    Purpose of the Study:

    • To investigate the adversarial robustness of deep one-class novelty detectors.
    • To propose a novel defense strategy tailored for novelty detection.
    • To enhance the resilience of novelty detection models against adversarial examples.

    Main Methods:

    • Demonstrated susceptibility of existing novelty detectors to adversarial examples.
    • Proposed Principal Latent Space (PrincipaLS) method.

    More Related Videos

    Cross-Modal Multivariate Pattern Analysis
    13:51

    Cross-Modal Multivariate Pattern Analysis

    Published on: November 9, 2011

    20.0K
    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

    627

    Related Experiment Videos

    Last Updated: Sep 5, 2025

    Novel Object Recognition and Object Location Behavioral Testing in Mice on a Budget
    05:57

    Novel Object Recognition and Object Location Behavioral Testing in Mice on a Budget

    Published on: November 20, 2018

    56.5K
    Cross-Modal Multivariate Pattern Analysis
    13:51

    Cross-Modal Multivariate Pattern Analysis

    Published on: November 9, 2011

    20.0K
    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

    627
  • PrincipaLS manipulates the latent space using incrementally-trained cascade principal components.

    • Main Results:

    • Common defense approaches showed limited effectiveness.
    • PrincipaLS successfully purified the latent space against adversarial examples.
    • Experiments across eight attacks, five datasets, and seven detectors confirmed consistent robustness enhancement.

    Conclusions:

    • Deep novelty detectors require specialized defenses against adversarial attacks.
    • PrincipaLS offers an effective strategy to improve adversarial robustness in one-class novelty detection.
    • The method constrains the latent space to accurately model the known class distribution.