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

Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

1.7K
Memory is one of the most vital higher mental functions of the brain. Memory is closely related to learning because it enables us to retain information and experiences from our past to use them in our present life. It also helps us to remember facts, events, and skills, such as riding a bike or swimming. There are two types of memory — declarative memory, which involves memorizing facts or events, and procedural memory, which enables us to remember how to do something like writing or...
1.7K
Neural Circuits01:25

Neural Circuits

2.1K
Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...
2.1K
Associative Learning01:27

Associative Learning

849
Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...
849
Storage01:23

Storage

217
A schema is a mental framework that helps individuals organize and interpret information. Schemata, formed from previous experiences, influence how we process new information: how we encode it, the inferences we make, and how we retrieve it. For instance, a schema for what a typical classroom looks like might include desks, a teacher's desk, a whiteboard, and students in such an environment. This expectation helps us quickly understand and navigate new classrooms without needing to analyze...
217
Role of Neurotransmitters in Memory01:23

Role of Neurotransmitters in Memory

2.0K
Neurotransmitters are integral to the brain's communication system, enabling neurons to transmit signals across synapses. This chemical exchange underpins various cognitive functions, including memory processes. The role of neurotransmitters in memory is multifaceted, influencing the encoding, consolidation, and retrieval of memories through their action on different neural circuits.
 Glutamate and Synaptic Plasticity
Glutamate, the brain's main excitatory neurotransmitter, is...
2.0K
Graded Potential01:19

Graded Potential

5.9K
Graded potentials are localized fluctuations in the cell membrane's electrical charge, commonly found in the dendrites of neurons. The magnitude of these potential changes depends on the strength of the initiating stimulus. In a membrane at its resting potential, a graded potential signifies a voltage shift either above -70 mV or below -70 mV.
Graded potentials fall into two categories: depolarizing and hyperpolarizing. Depolarizing graded potentials typically occur when sodium (Na+) or...
5.9K

You might also read

Related Articles

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

Sort by
Same author

Performance and mental workload dynamics during in-person and virtually-based remote learning of action sequences.

Ergonomics·2026
Same author

Using a self-modulated treadmill as a novel approach to study cognitive-motor and biomechanical outcomes during dual-task walking in individuals with and without lower limb loss.

Experimental brain research·2026
Same author

Revealing the brain signal complexity underlying superior putting performance in expert golfers: A multiscale entropy study with supplemental connectivity analyses.

Biological psychology·2025
Same author

Brain Biomarkers for Assessing Practice of Robotic Arm Reaching Movements Using a Head-Controlled Interface.

IEEE ... International Conference on Rehabilitation Robotics : [proceedings]·2025
Same author

Neurocognitive assessment under various human-robot teaming environments.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2025
Same author

A single session of sensorimotor rhythm neurofeedback enhances long-game performance in professional golfers.

Biological psychology·2024
Same journal

Dynamic analysis and reliable mechanical optimization application of ring HNN effected with a memristive neuron.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

DAFF-Net: A detection and search method for small-scale low surface brightness galaxies.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Quasi-synchronization for complex networks with hybrid pinning intermittent control.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Physics-encoded convolutional neural operators for parametric PDEs: A convergence-guaranteed framework via pre-computed kernel fields.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Nov 16, 2025

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans
07:17

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans

Published on: June 23, 2022

2.7K

Compositional memory in attractor neural networks with one-step learning.

Gregory P Davis1, Garrett E Katz2, Rodolphe J Gentili3

  • 1Department of Computer Science, University of Maryland, College Park, MD, USA.

Neural Networks : the Official Journal of the International Neural Network Society
|February 25, 2021
PubMed
Summary
This summary is machine-generated.

This study introduces a novel recurrent neural network for artificial intelligence that uses attractor graphs for compositional working memory. This approach enables efficient storage and retrieval of structured data, improving AI generalization capabilities.

Keywords:
CompositionalityItinerant attractor dynamicsMultiplicative gatingOne-step learningProgrammable neural networksWorking memory

More Related Videos

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

13.3K

Related Experiment Videos

Last Updated: Nov 16, 2025

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans
07:17

Aversive Associative Learning and Memory Formation by Pairing Two Chemicals in Caenorhabditis elegans

Published on: June 23, 2022

2.7K
Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees
13:55

Simultaneous Long-term Recordings at Two Neuronal Processing Stages in Behaving Honeybees

Published on: July 21, 2014

13.3K

Area of Science:

  • Artificial Intelligence
  • Cognitive Science
  • Computational Neuroscience

Background:

  • Compositionality is crucial for human-level AI, enabling reasoning through reusable components.
  • Traditional neural networks struggle with systematic, generalizable structured models due to memory limitations.
  • Short-term memory in neural networks often relies on persistent activity without rapid weight adjustments.

Purpose of the Study:

  • To develop a recurrent neural network capable of learning and implementing compositional working memory.
  • To address the limitations of current artificial neural networks in handling structured data and generalization.
  • To enhance artificial intelligence systems with robust compositional reasoning abilities.

Main Methods:

  • Introduced a recurrent neural network model using contextually-gated dynamical attractors (attractor graphs).
  • Implemented a functionally compositional working memory manipulated via top-down gating and fast local learning.
  • Evaluated the network on graph-based data structure storage/retrieval and automated hierarchical planning tasks.

Main Results:

  • Demonstrated successful storage and retrieval of compositional structures in neural working memory without persistent activity maintenance.
  • Showcased improved memory capacity through a fast store-erase learning rule for controlled association mutation.
  • Validated the network's ability to handle graph-based data and hierarchical planning.

Conclusions:

  • The combination of top-down gating and fast associative learning provides a robust mechanism for compositional working memory in recurrent neural networks.
  • This approach offers a promising pathway towards more generalizable and productive artificial intelligence systems.
  • The findings suggest a new direction for designing neural architectures that mimic human compositional reasoning.