Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Propagation of Uncertainty from Random Error

Propagation of Uncertainty from Random Error

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...

Propagation of Uncertainty from Systematic Error

Propagation of Uncertainty from Systematic Error

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...

Uncertainty: Overview

Uncertainty: Overview

In analytical chemistry, we often perform repetitive measurements to detect and minimize inaccuracies caused by both determinate and indeterminate errors. Despite the cares we take, the presence of random errors means that repeated measurements almost never have exactly the same magnitude. The collective difference between these measurements - observed values - and the estimated or expected value is called uncertainty. Uncertainty is conventionally written after the estimated or expected value.

Uncertainty: Confidence Intervals

Uncertainty: Confidence Intervals

The confidence interval is the range of values around the mean that contains the true mean. It is expressed as a probability percentage. The interpretation of a 95% confidence interval, for instance, is that the statistician is 95% confident that the true mean falls within the interval. The upper and lower limits of this range are known as confidence limits. The confidence limits for the true mean are estimated from the sample's mean, the standard deviation, and the statistical factor...

Classification of Systems-II

Classification of Systems-II

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,

Classification of Systems-I

Classification of Systems-I

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:

You might also read

Related Articles

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

Sort by

Same author

Interstitial Copper Doping and Thermally Activated Rattling in La<sub>3-</sub> <sub>x</sub>Te<sub>4</sub> for Enhanced Thermoelectric Performance.

Angewandte Chemie (International ed. in English)·2026

Same author

<i>In vitro</i> nephroprotective indolizidine alkaloids from marine-derived <i>Streptomyces</i> sp. KIB629.

Natural product research·2026

Same author

Sulfur Vacancy-Engineered 2D/2D ZnIn<sub>2</sub>S<sub>4</sub>/Zn-TCPP S-Scheme Heterojunction for Efficient Photocatalytic H<sub>2</sub>O<sub>2</sub> Production.

Small (Weinheim an der Bergstrasse, Germany)·2026

Same author

A Fully Automated Deep Learning Model for Quantifying Coronary Plaque at Coronary CT Angiography.

Radiology·2026

Same author

Survival advantage of conversion surgery following induction therapy in cT4 esophageal cancer: A systematic review and meta-analysis.

European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology·2026

Same author

Comparative genomics on chloroplasts of Chinese <i>Rubus</i>: genetic structure and phylogenetic relationships with other species of Rosaceae.

Frontiers in plant science·2026

Search research articles

Related Experiment Video

Updated: Jun 7, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Exploring the uncertainty principle in neural networks through binary classification.

Jun-Jie Zhang¹, Jian-Nan Chen¹, De-Yu Meng^2,3

¹Northwest Institute of Nuclear Technology, Xi'an, 710024, Shaanxi, China.

Scientific Reports

|November 17, 2024

Summary

This summary is machine-generated.

Neural networks exhibit an accuracy-robustness trade-off, where higher accuracy increases vulnerability to adversarial attacks. This study uses quantum mechanics principles to explain this inherent limitation in deep learning models.

Keywords:

Classification network Neural packet Uncertainty principle

More Related Videos

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Measuring the Subjective Value of Risky and Ambiguous Options using Experimental Economics and Functional MRI Methods

Measuring the Subjective Value of Risky and Ambiguous Options using Experimental Economics and Functional MRI Methods

Published on: September 19, 2012

Related Experiment Videos

Last Updated: Jun 7, 2025

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks

Published on: March 2, 2015

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Creating Objects and Object Categories for Studying Perception and Perceptual Learning

Published on: November 2, 2012

Measuring the Subjective Value of Risky and Ambiguous Options using Experimental Economics and Functional MRI Methods

Measuring the Subjective Value of Risky and Ambiguous Options using Experimental Economics and Functional MRI Methods

Published on: September 19, 2012

Area of Science:

Artificial Intelligence
Machine Learning
Quantum Mechanics

Background:

Neural networks are susceptible to adversarial attacks, with underlying mechanisms not fully understood.
Existing research lacks a quantitative measure for this vulnerability.

Purpose of the Study:

To explore the intrinsic trade-off between accuracy and robustness in neural networks.
To provide a theoretical foundation for understanding neural network vulnerabilities using quantum mechanics.
To reveal the inherent balance between feature extraction precision and adversarial perturbation susceptibility.

Main Methods:

Framing the accuracy-robustness trade-off through the lens of the "uncertainty principle".
Applying mathematical concepts from quantum mechanics to analyze neural network behavior.
Developing an analytical method to quantify vulnerabilities.

Main Results:

Demonstrated an inherent trade-off: increased neural network accuracy correlates with heightened vulnerability to adversarial attacks.
Identified the "uncertainty relation" as the root cause of this phenomenon.
Provided a theoretical framework and analytical tools for understanding deep learning model vulnerabilities.

Conclusions:

The study offers a novel perspective on neural network security by linking it to fundamental principles.
The findings suggest inherent limitations in achieving both high accuracy and robustness simultaneously.
The quantum mechanics-inspired approach provides a new avenue for developing more secure AI systems.