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

Non-equilibrium in the Cell01:16

Non-equilibrium in the Cell

4.1K
An important concept in studying metabolism and energy is that of chemical equilibrium. Most chemical reactions are reversible. They can proceed in both directions, releasing energy into their environment in one direction, and absorbing it from the environment in the other direction. The same is true for the chemical reactions involved in cell metabolism, such as the breaking down and building up of proteins into and from individual amino acids, respectively. Reactants within a closed system...
4.1K
Concepts and Prototypes01:24

Concepts and Prototypes

70
The human nervous system handles vast amounts of information by translating sensory stimuli into neural impulses, which the brain processes, creating thoughts expressed through language or stored as memories. The brain also synthesizes information from emotions and memories, which significantly influence thoughts and behaviors. This intricate process creates a comprehensive mental picture.
The brain organizes this information using concepts, which are mental categories grouping linguistic data,...
70
Stereotype Content Model02:16

Stereotype Content Model

13.9K
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...
13.9K
Natural and Artificial Concepts01:24

Natural and Artificial Concepts

94
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...
94
Cognitive Learning01:21

Cognitive Learning

114
Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
114
High-Level and Low-Level Awareness01:19

High-Level and Low-Level Awareness

244
Controlled processes in human consciousness represent high-alert mental states where individuals deliberately focus their attention on achieving specific goals. Controlled processes can be seen in situations like mastering new technology, where a person might become so absorbed that they ignore surrounding distractions. Such processes involve selective attention, requiring one to concentrate on particular elements of experience while disregarding others. These are governed by executive...
244

You might also read

Related Articles

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

Sort by
Same author

Accelerating scientific discovery with Co-Scientist.

ArXiv·2026
Same author

AI-Discovered Cognitive Models Reveal Novel Insights into Human and Animal Learning.

bioRxiv : the preprint server for biology·2026
Same author

Accelerating scientific discovery with Co-Scientist.

Nature·2026
Same author

A framework for clinical validation of generative artificial intelligence therapeutics.

World psychiatry : official journal of the World Psychiatric Association (WPA)·2026
Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026
Same author

Advancing regulatory variant effect prediction with AlphaGenome.

Nature·2026

Related Experiment Video

Updated: May 20, 2025

The HoneyComb Paradigm for Research on Collective Human Behavior
06:48

The HoneyComb Paradigm for Research on Collective Human Behavior

Published on: January 19, 2019

9.3K

Bridging the human-AI knowledge gap through concept discovery and transfer in AlphaZero.

Lisa Schut1, Nenad Tomašev2, Thomas McGrath3

  • 1Oxford Applied and Theoretical Machine Learning Group, Department of Computer Science, University of Oxford, Oxford OX1 3QG, United Kingdom.

Proceedings of the National Academy of Sciences of the United States of America
|March 26, 2025
PubMed
Summary
This summary is machine-generated.

Researchers developed a method to extract novel chess concepts from AlphaZero, an AI system. These concepts improved grandmasters' performance, demonstrating AI

Keywords:
AIconcept discoverymachine learningreinforcement learning

More Related Videos

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
Author Spotlight: Investigating the Effects of Mind-Body-Movement Practices on Brain Function
06:17

Author Spotlight: Investigating the Effects of Mind-Body-Movement Practices on Brain Function

Published on: January 26, 2024

1.8K

Related Experiment Videos

Last Updated: May 20, 2025

The HoneyComb Paradigm for Research on Collective Human Behavior
06:48

The HoneyComb Paradigm for Research on Collective Human Behavior

Published on: January 19, 2019

9.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.2K
Author Spotlight: Investigating the Effects of Mind-Body-Movement Practices on Brain Function
06:17

Author Spotlight: Investigating the Effects of Mind-Body-Movement Practices on Brain Function

Published on: January 26, 2024

1.8K

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Game Theory

Background:

  • Artificial intelligence (AI) systems exhibit superhuman performance in various domains.
  • Extracting internal knowledge from AI is challenging due to vast representational spaces.
  • Leveraging AI knowledge could significantly advance human understanding and capabilities.

Purpose of the Study:

  • To develop a method for extracting novel and teachable concepts from AI.
  • To validate the utility of extracted AI concepts in advancing human knowledge.
  • To demonstrate the potential of AI as a source for new conceptual discoveries.

Main Methods:

  • Excavating concept vectors from AlphaZero's internal representations using convex optimization.
  • Filtering extracted concepts based on teachability and novelty criteria.
  • Validating concepts through expert assessment using chess puzzle-solution prototypes.

Main Results:

  • A novel method successfully extracted meaningful chess concepts from AlphaZero.
  • Extracted concepts were transferable to another AI agent and contained novel information.
  • Chess grandmasters showed performance improvement after learning the AI-derived concepts.
  • The concepts were found to be at the edge of current human chess understanding.

Conclusions:

  • AI systems can serve as a source for discovering new knowledge beyond human expertise.
  • The developed method provides a proof of concept for leveraging AI knowledge extraction.
  • This approach has profound implications for advancing human knowledge and human-AI interaction across applications.