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

Survival Tree01:19

Survival Tree

126
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
126
Stereotype Content Model02:16

Stereotype Content Model

14.8K
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence...
14.8K
Classification of Systems-I01:26

Classification of Systems-I

236
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:
236
Force Classification01:22

Force Classification

1.3K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.3K
Classification of Systems-II01:31

Classification of Systems-II

192
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,
192
Natural and Artificial Concepts01:24

Natural and Artificial Concepts

223
In psychology, concepts can be divided into two categories: natural and artificial. Natural concepts are formed through direct or indirect experiences. For example, consider the concept of snow. If you live in a place with regular snowfall, such as Essex Junction, Vermont, you know snow through direct experiences. You’ve seen it fall, touched it, shoveled it, and played in it. You recognize its texture, appearance, and even its smell. In contrast, if you live on an island like Saint...
223

You might also read

Related Articles

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

Sort by
Same author

Bending behavior of concrete-filled FRP wound tubular arches with internal FRP bars.

Scientific reports·2026
Same author

Pretending Not to Know Reveals a Capacity for Model-Based Self-Simulation.

Psychological science·2026
Same author

A unifying account of replay as context-driven memory reactivation.

eLife·2026
Same author

Part-whole effects in visual number estimation.

Attention, perception & psychophysics·2026
Same author

Prediction models and associated uncertainty for dynamic shear modulus and damping ratio of Beijing silty clay.

Scientific reports·2025
Same author

MAPCliff-WMGR: Exploring Activity Cliffs in Molecular Activity Prediction Enhanced by Weighted Molecular Graph Representations.

Journal of chemical information and modeling·2025

Related Experiment Video

Updated: Aug 4, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

906

When will AI misclassify? Intuiting failures on natural images.

Makaela Nartker1,2, Zhenglong Zhou3,4, Chaz Firestone1,5

  • 1Department of Psychological & Brain Sciences, Johns Hopkins University, Baltimore, MD, USA.

Journal of Vision
|April 6, 2023
PubMed
Summary

Ordinary people can predict when and how artificial intelligence (AI) image recognition systems will misclassify natural images. This research explores human intuition about AI

More Related Videos

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K

Related Experiment Videos

Last Updated: Aug 4, 2025

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

906
Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence
09:11

Automation of the Micronucleus Assay Using Imaging Flow Cytometry and Artificial Intelligence

Published on: January 27, 2023

2.2K
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K

Area of Science:

  • Computer Vision
  • Artificial Intelligence
  • Cognitive Science

Background:

  • Machine recognition systems excel at natural image classification but fail unexpectedly on specific inputs.
  • These failures, termed 'natural adversarial examples', involve unmodified images that consistently fool AI systems (e.g., a bird's shadow misclassified as a sundial).

Purpose of the Study:

  • To investigate whether naive human observers can predict AI misclassifications of natural images.
  • To determine if humans can anticipate both the occurrence and the nature of these AI errors.

Main Methods:

  • Five experiments were conducted using natural adversarial examples.
  • Participants predicted which images AI systems would misclassify and how.
  • Experiments varied conditions, including forced-choice and continuous stream presentations.

Main Results:

  • Subjects accurately predicted which natural images would fool machine recognition systems.
  • Participants could also anticipate the specific misclassifications made by the AI.
  • These predictive abilities were robust across different experimental conditions.

Conclusions:

  • Ordinary people possess an intuitive understanding of image classification difficulty for AI.
  • This human ability to anticipate AI errors has implications for human-machine teams and AI safety.
  • Findings highlight the interplay between biological and artificial vision systems.