Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Classification of Systems-I

Classification of Systems-I

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:

Linear time-invariant Systems

Linear time-invariant Systems

A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be...

Associative Learning

Associative Learning

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...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

Observational Learning

Observational Learning

Albert Bandura's observational learning, also known as imitation or modeling, occurs when a person observes and imitates another's behavior. It is a quicker process than operant conditioning. A well-known example is the Bobo doll study, where children who saw an adult acting aggressively towards the doll were more likely to act aggressively when left alone, compared to those who observed a nonaggressive adult. Many psychologists view observational learning as a form of latent learning...

Introduction to Learning

Introduction to Learning

Learning is the process of acquiring knowledge or skills through practice or experience, leading to long-lasting behavioral changes. This acquisition occurs through interaction with the environment and requires practice or experience. For instance, mastering a skill such as surfing requires considerable practice and experience, highlighting the essential role of repeated interactions with the environment in learning.
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...

You might also read

Related Articles

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

Sort by

Same author

The Case for Local AI Development: Lessons From Computer‑Aided Detection of Tuberculosis and Silicosis in Southern Africa's Ex‑Miners.

Annals of global health·2026

Same author

Organizing memories for generalization in complementary learning systems.

Nature neuroscience·2023

Same author

Metamodal Coupling of Vibrotactile and Auditory Speech Processing Systems through Matched Stimulus Representations.

The Journal of neuroscience : the official journal of the Society for Neuroscience·2023

Same author

Strategically managing learning during perceptual decision making.

eLife·2023

Same author

Adverse Events in Pediatric Critical Care Nonsurvivors With a Low Predicted Mortality Risk: A Multicenter Case Control Study.

Pediatric critical care medicine : a journal of the Society of Critical Care Medicine and the World Federation of Pediatric Intensive and Critical Care Societies·2022

Same author

If deep learning is the answer, what is the question?

Nature reviews. Neuroscience·2020

Same journal

The TaMYB55-TaSnRK1α1-TabZIP9 module confers heat stress tolerance in wheat.

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

Same journal

Superstatistics approach to turbulent circulation fluctuations.

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

Same journal

A molecular timescale for evolution of cobamide biosynthesis.

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

Same journal

Pierre Chambon, a pioneer of molecular biology and gene regulation in eukaryotes.

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

Same journal

Granulosa cell glycogen fuels the avascular corpus luteum.

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

Same journal

Synthetic essentiality of TRAIL/TNFSF10 in VHL-deficient renal cell carcinoma.

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

See all related articles

Search research articles

Related Experiment Video

Updated: May 7, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Compositionality and systematicity emerge from iterated learning in deep linear networks.

Devon Jarvis^1,2, Richard Klein^1,2, Benjamin Rosman^1,2

¹School of Computer Science and Applied Mathematics, University of the Witwatersrand, Johannesburg 2000, South Africa.

Proceedings of the National Academy of Sciences of the United States of America

|May 5, 2026

Summary

This summary is machine-generated.

Iterated learning enhances systematic generalization in neural networks by fostering compositional language structures over multiple generations. This method, however, requires extensive datasets to achieve robust generalization.

Keywords:

iterated Learning linear neural networks systematic generalization

More Related Videos

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

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

Published on: March 2, 2015

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Related Experiment Videos

Last Updated: May 7, 2026

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

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

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

Published on: March 2, 2015

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

A Virtual Machine Platform for Non-Computer Professionals for Using Deep Learning to Classify Biological Sequences of Metagenomic Data

Published on: September 25, 2021

Area of Science:

Cognitive Science
Artificial Intelligence
Computational Linguistics

Background:

Human systematic generalization involves reasoning about novel situations using prior experiences.
Language serves as a prime example of systematic generalization, inspiring machine learning models.
Iterated learning, a machine learning paradigm, involves sequential generations of networks learning from predecessors.

Purpose of the Study:

To theoretically investigate the emergence of compositional language in neural networks.
To analyze how iterated learning facilitates systematic generalization.
To refine the definition of systematicity and understand its benefits and limitations within iterated learning.

Main Methods:

Analysis of shallow and deep linear networks applied to iterated learning dynamics.
Derivation of exact learning dynamics across multiple generations.
Refinement of the definition of systematicity for iterated learning.

Main Results:

Iterated learning promotes systematic generalization by uncovering compositional substructure in output labels.
Multiple generations of iterated learning are necessary for compositional structure emergence.
Performance of iterated learning can surpass single-generation networks with early stopping.

Conclusions:

Iterated learning effectively facilitates systematic generalization compared to standard training.
Emergent systematicity requires extensive datasets, leading to the definition of 'weak systematic generalization'.
The study confirms the necessity of multiple learning generations for compositional structure development.