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

Ampere-Maxwell's Law: Problem-Solving01:17

Ampere-Maxwell's Law: Problem-Solving

824
A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...
824
Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving01:29

Mechanistic Models: Compartment Models in Algorithms for Numerical Problem Solving

123
Mechanistic models play a crucial role in algorithms for numerical problem-solving, particularly in nonlinear mixed effects modeling (NMEM). These models aim to minimize specific objective functions by evaluating various parameter estimates, leading to the development of systematic algorithms. In some cases, linearization techniques approximate the model using linear equations.
In individual population analyses, different algorithms are employed, such as Cauchy's method, which uses a...
123
The Role of Ion Channels in Neuronal Computation01:19

The Role of Ion Channels in Neuronal Computation

3.3K
A postsynaptic neuron usually receives numerous impulses from several other presynaptic neurons. The axon hillock of the postsynaptic neuron integrates all these signals and determines the likelihood of firing an action potential.
Sometimes a single EPSP is strong enough to induce an action potential in the postsynaptic neuron. However, multiple presynaptic inputs must often create EPSPs around the same time for the postsynaptic neuron to be sufficiently depolarized to fire an action potential....
3.3K
Normal and Tangetial Components: Problem Solving01:24

Normal and Tangetial Components: Problem Solving

318
Consider a man with a mass of 70 kg seated in a chair connected to a pin support through a member BC. If the man maintains an upright position, the task is to determine the horizontal and vertical reactions of the chair on the man when the member makes a 45° angle with the horizontal. At this moment, the man has a speed of 5 m/s, increasing at a rate of 1 m/s².
318
Parallel Processing01:20

Parallel Processing

358
The brain processes sensory information rapidly due to parallel processing, which involves sending data across multiple neural pathways at the same time. This method allows the brain to manage various sensory qualities, such as shapes, colors, movements, and locations, all concurrently. For instance, when observing a forest landscape, the brain simultaneously processes the movement of leaves, the shapes of trees, the depth between them, and the various shades of green. This enables a quick and...
358
Gauss's Law: Problem-Solving01:10

Gauss's Law: Problem-Solving

2.2K
Gauss's law helps determine electric fields even though the law is not directly about electric fields but electric flux. In situations with certain symmetries (spherical, cylindrical, or planar) in the charge distribution, the electric field can be deduced based on the knowledge of the electric flux. In these systems, we can find a Gaussian surface S over which the electric field has a constant magnitude. Furthermore, suppose the electric field is parallel (or antiparallel) to the area...
2.2K

You might also read

Related Articles

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

Sort by
Same author

Evaluating the robustness and readiness of large frontier models in health AI applications.

Nature medicine·2026
Same author

Desert <i>Chlorella</i> Malate Synthase 1 Enhances Salt Tolerance by Promoting Soluble Sugar and Lipid Accumulation.

Plants (Basel, Switzerland)·2026
Same author

ProtSATT: An Advanced Protein Solubility Predictor Based on Attention Mechanism.

Journal of chemical information and modeling·2026
Same author

Lessons Learned in the Early Adoption of Method of Detection Reporting.

Journal of breast imaging·2026
Same author

False-Negative Screening and Diagnostic Mammograms in the National Mammography Database From 2010 to 2022.

AJR. American journal of roentgenology·2025
Same author

Natural products inhibit inflammatory diseases by regulating macrophage polarization.

International immunopharmacology·2025
Same journal

How the Stroop Effect Arises from Optimal Response Times in Laterally Connected Self-Organizing Maps.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2026
Same journal

Development in the comprehension of phonetically reduced spoken words.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2025
Same journal

Symbolic numerical generalization through representational alignment.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2025
Same journal

Backward reasoning through AND/OR trees to solve problems.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2025
Same journal

When Hearing Lips and Seeing Voices Becomes Perceiving Speech: Auditory-Visual Integration in Lexical Access.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2024
Same journal

Effect of Fatigue on Word Production in Aphasia.

CogSci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference·2024
See all related articles

Related Experiment Video

Updated: Oct 17, 2025

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

692

Compositional Processing Emerges in Neural Networks Solving Math Problems.

Jacob Russin1, Roland Fernandez2, Hamid Palangi2

  • 1Department of Psychology, UC Davis.

Cogsci ... Annual Conference of the Cognitive Science Society. Cognitive Science Society (U.S.). Conference
|October 7, 2021
PubMed
Summary
This summary is machine-generated.

Neural networks learn compositionality, mirroring human cognition. They infer structured relationships in data and use this to combine simple meanings into complex ones, applicable to mathematical reasoning.

Keywords:
compositionalitymathematical cognitionneural networksreasoning

More Related Videos

Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

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

Published on: March 2, 2015

10.5K

Related Experiment Videos

Last Updated: Oct 17, 2025

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

692
Closed-loop Neuro-robotic Experiments to Test Computational Properties of Neuronal Networks
11:18

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

Published on: March 2, 2015

10.5K

Area of Science:

  • Cognitive Science
  • Artificial Intelligence
  • Computational Linguistics

Background:

  • Human cognition exhibits compositionality, enabling the inference and application of structured relationships.
  • Artificial neural networks (ANNs) demonstrate emergent grammatical structure from linguistic data.
  • The mechanisms of learning compositionality remain a key question in cognitive science.

Purpose of the Study:

  • To investigate if ANNs can learn and apply compositionality beyond linguistic tasks.
  • To extend research on emergent structure in ANNs to the domain of mathematical reasoning.
  • To test hypotheses on how ANNs compose meanings based on structured rules.

Main Methods:

  • Training large-scale neural networks on mathematical reasoning tasks.
  • Formulating precise hypotheses on meaning composition using mathematical rules (e.g., order of operations).
  • Analyzing ANN representations to identify inferred structured relationships.

Main Results:

  • Neural networks successfully inferred structured relationships implicit in mathematical training data.
  • Trained ANNs demonstrated the ability to deploy learned knowledge for meaning composition.
  • ANNs composed individual numerical meanings into complex wholes guided by inferred rules.

Conclusions:

  • ANNs can learn and apply compositional principles, analogous to human cognitive abilities.
  • This research extends the understanding of emergent structure in ANNs to mathematical domains.
  • Findings suggest ANNs can generalize learned compositional knowledge to new reasoning tasks.