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

Classification of Systems-I01:26

Classification of Systems-I

543
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
543
Classification of Systems-II01:31

Classification of Systems-II

449
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
449
Aggregates Classification01:29

Aggregates Classification

960
Aggregate classification is generally based on its size, petrographic characteristics, weight, and source. Size classification ranges from coarse to fine aggregates, defined by the size of the particles. Coarse aggregates are particles that do not pass through ASTM sieve No. 4, and aggregates that pass through the sieve are fine aggregates.
Petrographic classification groups aggregates based on common mineralogical characteristics. Some of the common mineral groups found in aggregates are...
960
Classification of Signals01:30

Classification of Signals

1.3K
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...
1.3K
Accuracy and Precision01:52

Accuracy and Precision

13.9K
Scientists typically make repeated measurements of a quantity to ensure the quality of their findings and to evaluate both the precision and the accuracy of their results. Measurements are said to be precise if they yield very similar results when repeated in the same manner. A measurement is considered accurate if it yields a result that is very close to the true or the accepted value. Precise values agree with each other; accurate values agree with a true value.  Highly accurate...
13.9K
Accuracy, limits, and approximation01:28

Accuracy, limits, and approximation

1.1K
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...
1.1K

You might also read

Related Articles

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

Sort by
Same author

CD20-targeted immunotherapies in B-cell malignancies: mechanistic and clinical advances.

Experimental hematology·2026
Same author

Albumin Binding as a Strategy for Improving Tumor Targeting of Radiolabeled Compounds.

Molecular pharmaceutics·2025
Same author

Targeted Delivery of Bortezomib Using Retinoid-Based Nanoparticle: Modulating Liver Fibrosis through the TGF-β1/Smad3 Pathway.

Advanced pharmaceutical bulletin·2025
Same author

Design, synthesis, and optimization of a novel ternary photocatalyst for degradation of cephalexin antibiotic in aqueous solutions.

Scientific reports·2025
Same author

Mitochondrial transplantation for cardioprotection and induction of angiogenesis in ischemic heart disease.

Stem cell research & therapy·2025
Same author

MicroRNAs' Significance in Retinoblastoma Diagnosis and Treatment: The Little Heroes.

Biochemical genetics·2025

Related Experiment Video

Updated: Jan 11, 2026

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
06:22

Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

Published on: September 19, 2025

414

On Continuity of Robust and Accurate Classifiers.

Ramin Barati, Reza Safabakhsh, Mohammad Rahmati

    IEEE Transactions on Neural Networks and Learning Systems
    |November 11, 2025
    PubMed
    Summary
    This summary is machine-generated.

    Continuity in machine learning models hinders robustness and accuracy against adversarial attacks. Discontinuous hypotheses are proposed as a solution for creating more reliable and accurate learning models.

    More Related Videos

    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.6K
    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
    07:35

    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

    Published on: October 11, 2018

    7.9K

    Related Experiment Videos

    Last Updated: Jan 11, 2026

    Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
    06:22

    Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections

    Published on: September 19, 2025

    414
    Assessment and Communication for People with Disorders of Consciousness
    07:37

    Assessment and Communication for People with Disorders of Consciousness

    Published on: August 1, 2017

    9.6K
    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
    07:35

    Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

    Published on: October 11, 2018

    7.9K

    Area of Science:

    • Machine Learning
    • Theoretical Computer Science
    • Robustness in AI

    Background:

    • Adversarial attacks pose a significant threat to machine learning model reliability.
    • Adversarial training improves robustness but often reduces accuracy on natural samples, suggesting a trade-off between robustness and accuracy.
    • The prevailing view is that model robustness and accuracy are inherently conflicting goals.

    Purpose of the Study:

    • To challenge the notion that robustness and accuracy are incompatible.
    • To propose that the continuity of a hypothesis is the limiting factor for achieving both robustness and accuracy.
    • To introduce a framework for studying harmonic and holomorphic hypotheses in learning theory.

    Main Methods:

    • Developed a theoretical framework for analyzing harmonic and holomorphic hypotheses.
    • Conducted empirical studies comparing the performance of continuous versus discontinuous hypotheses on common machine learning tasks.
    • Analyzed the adversarial examples phenomenon as a conflict between function sequence continuity and uniform convergence to discontinuous functions.

    Main Results:

    • Empirical evidence shows that continuous hypotheses underperform discontinuous ones in certain machine learning tasks.
    • Continuous functions struggle to learn optimal robust hypotheses.
    • The study provides a theoretical explanation for the adversarial examples phenomenon.

    Conclusions:

    • Continuity, not robustness vs. accuracy, is incompatible with optimal performance in many machine learning scenarios.
    • Discontinuous hypotheses are essential for developing robust and accurate machine learning models.
    • The findings have practical implications for designing learning rules and theoretical implications for understanding model behavior and evaluation.