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

Causes of Similarity-Dissimilarity Effect01:26

Causes of Similarity-Dissimilarity Effect

347
The similarity-dissimilarity effect, a fundamental concept in social psychology, explains how interpersonal similarities and differences influence attraction and social interactions. This effect is supported by three key psychological perspectives: balance theory, social comparison theory, and consensual validation.Balance Theory and Cognitive ConsistencyBalance theory, developed by Fritz Heider, posits that individuals seek cognitive consistency in their relationships. When two people share...
347
Neural Circuits01:25

Neural Circuits

3.3K
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...
3.3K
Associative Learning01:27

Associative Learning

1.9K
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...
1.9K
Observational Learning01:12

Observational Learning

1.3K
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...
1.3K
Long-term Potentiation01:25

Long-term Potentiation

3.9K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
Hebbian LTP
LTP can occur when...
3.9K
Long-term Potentiation01:35

Long-term Potentiation

59.6K
Long-term potentiation, or LTP, is one of the ways by which synaptic plasticity—changes in the strength of chemical synapses—can occur in the brain. LTP is the process of synaptic strengthening that occurs over time between pre- and postsynaptic neuronal connections. The synaptic strengthening of LTP works in opposition to the synaptic weakening of long-term depression (LTD) and together are the main mechanisms that underlie learning and memory.
59.6K

You might also read

Related Articles

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

Sort by
Same author

Distributionally robust free energy principle for decision-making.

Nature communications·2025
Same author

Firing Rate Models as Associative Memory: Synaptic Design for Robust Retrieval.

Neural computation·2025
Same author

Feasibility and Safety of a Three-Dimensional Sheath for Right Ventricular Septal Endomyocardial Biopsy.

Catheterization and cardiovascular interventions : official journal of the Society for Cardiac Angiography & Interventions·2025
Same author

Comparative Effectiveness of Midazolam-Based Sedation on the Need for Intracranial Pressure Lowering Therapies in Traumatic Brain Injury.

Neurotrauma reports·2025
Same author

Input-driven dynamics for robust memory retrieval in Hopfield networks.

Science advances·2025
Same author

Composite Nanostructures for the Production of White Light.

Molecules (Basel, Switzerland)·2024
Same journal

A Model-Free Reinforcement Learning Implementation of Decision Making Under Uncertainty by Sequential Sampling.

Neural computation·2026
Same journal

DROP: Distributional and Regular Optimism and Pessimism for Reinforcement Learning.

Neural computation·2026
Same journal

Hierarchical Active Inference Using Successor Representations.

Neural computation·2026
Same journal

W-Kernel and Its Principal Space for Frequentist Evaluation of Bayesian Estimators.

Neural computation·2026
Same journal

A Hidden Markov Model-Inspired Sequence Classification Method for Hyperdimensional Computing.

Neural computation·2026
Same journal

Sparse Graphical Modeling for Electrophysiological Phase-Based Connectivity Using Circular Statistics.

Neural computation·2026
See all related articles

Related Experiment Video

Updated: Apr 9, 2026

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.8K

Similarity Matching Networks: Hebbian Learning and Convergence Over Multiple Timescales.

Veronica Centorrino1, Francesco Bullo2, Giovanni Russo3

  • 1Department of Information and Electric Engineering and Applied Mathematics, University of Salerno, 84084 Fisciano SA, Italy vcentorrino@control.ee.ethz.ch.

Neural Computation
|April 7, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a biologically plausible neural network for dimensionality reduction, proving its convergence for principal subspace projection using a multilevel optimization framework and novel learning rules.

More Related Videos

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

10.4K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

3.1K

Related Experiment Videos

Last Updated: Apr 9, 2026

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time
07:12

Using Informational Connectivity to Measure the Synchronous Emergence of fMRI Multi-voxel Information Across Time

Published on: July 1, 2014

12.8K
Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
10:45

Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays

Published on: May 29, 2017

10.4K
A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments
08:12

A Psychophysics Paradigm for the Collection and Analysis of Similarity Judgments

Published on: March 1, 2022

3.1K

Area of Science:

  • Computational Neuroscience
  • Machine Learning
  • Matrix Analysis

Background:

  • Biologically plausible normative frameworks for dimensionality reduction often use similarity matching and low-rank matrix approximation.
  • While biologically interpretable and experimentally validated, a complete convergence analysis for these frameworks has been missing.
  • Principal subspace projection is a key task in dimensionality reduction with applications in various domains.

Purpose of the Study:

  • To formally analyze the convergence of a continuous-time neural network, the similarity matching network, for principal subspace projection.
  • To build upon existing biologically plausible frameworks by providing a rigorous mathematical foundation.
  • To demonstrate the network's effectiveness through theoretical analysis and numerical validation.

Main Methods:

  • Developed a continuous-time neural network (similarity matching network) based on a min-max-min objective.
  • The network features three coupled dynamics (neural, lateral synaptic, feedforward synaptic) operating at distinct timescales (fast, intermediate, slow).
  • Employed a multilevel optimization framework to analyze convergence, incorporating Hebbian and anti-Hebbian learning rules for synaptic dynamics.

Main Results:

  • Proved global exponential convergence of gradient-flow dynamics at the fast timescale (neural dynamics) due to strong convexity.
  • Established exponential convergence within positive definite matrices at the intermediate timescale (lateral synaptic dynamics) via strong concavity.
  • Demonstrated almost sure convergence to global minima for the nonconvex, nonsmooth cost function at the slow timescale (feedforward synaptic dynamics).

Conclusions:

  • The similarity matching network achieves provable convergence for principal subspace projection, addressing a key gap in normative framework analysis.
  • The multilevel optimization framework and timescale-separated dynamics provide a robust method for analyzing complex neural network behaviors.
  • The theoretical results, supported by numerical experiments and empirically motivated conjectures, validate the network's effectiveness.