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

Generalization, Discrimination, and Extinction01:24

Generalization, Discrimination, and Extinction

1.3K
Generalization, discrimination, and extinction are key concepts in operant conditioning that influence how behaviors are learned and maintained.
Generalization occurs when a behavior reinforced in one context is performed in similar situations. For instance, a student who studies diligently for calculus and receives excellent grades might apply the same study habits to psychology and history, expecting similar results. Generalization shows how learning in one setting can influence behavior in...
1.3K
Associative Learning01:27

Associative Learning

1.1K
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...
1.1K
Encoding01:19

Encoding

695
Information enters the brain through encoding, which is the input of information into the memory system. Once sensory information is received from the environment, the brain labels or codes it. The information is then organized with similar information and connected to existing concepts. Encoding occurs through automatic processing and effortful processing.
Automatic processing involves the encoding of details like time, space, frequency, and the meaning of words, usually done without conscious...
695
Higher Mental Functions of Brain: Learning and Memory01:26

Higher Mental Functions of Brain: Learning and Memory

1.9K
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...
1.9K
Storage01:23

Storage

303
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...
303
Neural Circuits01:25

Neural Circuits

2.5K
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...
2.5K

You might also read

Related Articles

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

Sort by
Same author

Studies with impossible languages falsify LMs as models of human language.

The Behavioral and brain sciences·2026
Same author

Correlations without causation do not support claims of human-LLM reasoning alignment.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

The successes and failures of artificial neural networks (ANNs) highlight the importance of innate linguistic priors for human language acquisition.

Psychological review·2025
Same author

Adapting to time: Why nature may have evolved a diverse set of neurons.

PLoS computational biology·2024
Same author

Clarifying status of DNNs as models of human vision.

The Behavioral and brain sciences·2023
Same author

The hazards of dealing with response time outliers.

Frontiers in psychology·2023

Related Experiment Video

Updated: Jan 1, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

517

Training neural networks to encode symbols enables combinatorial generalization.

Ivan I Vankov1, Jeffrey S Bowers2

  • 1Department of Cognitive Science and Psychology, New Bulgarian University, Sofia, Bulgaria.

Philosophical Transactions of the Royal Society of London. Series B, Biological Sciences
|December 17, 2019
PubMed
Summary

Neural networks can achieve combinatorial generalization, the ability to combine familiar elements into novel concepts, using a new method called the vectors approach to representing symbols (VARS). This approach enables standard neural architectures to encode symbolic knowledge, overcoming a major challenge in artificial intelligence.

Keywords:
combinatorial generalizationneural networkssymbols

More Related Videos

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K
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

10.7K

Related Experiment Videos

Last Updated: Jan 1, 2026

Decoding Natural Behavior from Neuroethological Embedding
08:00

Decoding Natural Behavior from Neuroethological Embedding

Published on: October 3, 2025

517
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K
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

10.7K

Area of Science:

  • Cognitive Science
  • Artificial Intelligence
  • Computational Neuroscience

Background:

  • Combinatorial generalization is a key human cognitive ability and a significant challenge for conventional neural networks.
  • Existing research suggests standard neural networks require specialized mechanisms for symbolic representation to achieve this ability.

Purpose of the Study:

  • To introduce a novel method, the vectors approach to representing symbols (VARS), for encoding symbolic structures in connectionist models.
  • To demonstrate that standard neural architectures can learn VARS representations and achieve combinatorial generalization.

Main Methods:

  • Developed the vectors approach to representing symbols (VARS) to represent symbolic structures in connectionist terms.
  • Trained standard neural network architectures using the VARS method.
  • Evaluated the networks' ability to produce VARS representations and achieve combinatorial generalization in simulations.

Main Results:

  • Neural networks successfully learned to produce VARS representations.
  • Networks demonstrated combinatorial generalization in both symbolic and non-symbolic outputs.
  • The VARS approach enabled standard architectures to encode symbolic knowledge explicitly.

Conclusions:

  • Standard neural networks can achieve combinatorial generalization without specialized symbolic mechanisms, using the VARS approach.
  • The VARS method offers a viable way to integrate symbolic processing within connectionist models.
  • This research questions the necessity of specific mechanisms or training routines for symbolic processing in neural networks.