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

Gradient and Del Operator01:14

Gradient and Del Operator

4.3K
In mathematics and physics, the gradient and del operator are fundamental concepts used to describe the behavior of functions and fields in space. The gradient is a mathematical operator that gives both the magnitude and direction of the maximum spatial rate of change. Consider a person standing on a mountain. The slope of the mountain at any given point is not defined unless it is quantified in a particular direction. For this reason, a "directional derivative" is defined, which is a vector...
4.3K
Regression Toward the Mean01:52

Regression Toward the Mean

6.8K
Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...
6.8K
Observational Learning01:12

Observational Learning

804
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...
804
Introduction to Learning01:18

Introduction to Learning

912
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...
912
Purposive Learning01:22

Purposive Learning

428
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
428
What is Natural Selection?01:32

What is Natural Selection?

125.6K
Natural selection is an evolutionary process in which individuals with survival-promoting traits reproduce at higher rates. These favorable traits become more common within a population or species. Naturally selected traits initially arise via random genetic mutations. In order for selection to occur, there must be variation within a population, the trait controlling the variation must be heritable, and there must be an evolutionary advantage for variation in the trait.
125.6K

You might also read

Related Articles

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

Sort by
Same author

Immediate changes in thoracic spine mobility after repetitive pitching in high school baseball players: A randomized controlled trial.

PM & R : the journal of injury, function, and rehabilitation·2026
Same author

Three fluoroquinolones with different epithelial lining fluid penetration in a murine lung infection model: an experimental site-specific PK/PD study.

Antimicrobial agents and chemotherapy·2026
Same author

Functional Shoulder Adaptations and Attack Form in High School Volleyball Players: Sex Differences in Range of Motion, Strength, and Dynamic Stability.

Sports health·2026
Same author

Toothpastes containing potassium nitrate alone versus potassium nitrate combined with aluminum lactate in reducing dentin hypersensitivity: a randomized controlled trial.

BDJ open·2026
Same author

Advances in causal discovery methods for ecological time series.

Biological reviews of the Cambridge Philosophical Society·2026
Same author

Medial elbow joint space gap after 100 pitches and early multi-sport participation in high school baseball players: a randomized controlled trial.

The Physician and sportsmedicine·2026
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: Jan 11, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Effective Learning Rules as Natural Gradient Descent.

Lucas Shoji1, Kenta Suzuki2, Leo Kozachkov3,4

  • 1Department of Physics and Department of Brain and Cognitive Sciences, MIT, Cambridge, MA 02139, USA lshoji@mit.edu.

Neural Computation
|November 14, 2025
PubMed
Summary
This summary is machine-generated.

Effective learning rules can be unified as natural gradient descent. This finding reveals the gradient as a fundamental element across diverse learning processes, with broad implications for AI and neuroscience.

More Related Videos

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients
07:34

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients

Published on: August 22, 2018

8.6K

Related Experiment Videos

Last Updated: Jan 11, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients
07:34

Probing the Limits of Egg Recognition Using Egg Rejection Experiments Along Phenotypic Gradients

Published on: August 22, 2018

8.6K

Area of Science:

  • Machine Learning
  • Computational Neuroscience
  • Control Theory

Background:

  • Learning rules aim to optimize performance over time.
  • Current learning rules are diverse and often specialized.
  • A unified mathematical framework for learning is lacking.

Purpose of the Study:

  • To establish a general mathematical framework for effective learning rules.
  • To demonstrate that a broad class of learning rules are instances of natural gradient descent.
  • To unify understanding of gradient-based optimization in learning.

Main Methods:

  • Expressing learning rules as natural gradient descent.
  • Defining appropriate information metrics for different learning settings.
  • Analyzing parameter updates using matrix calculus.

Main Results:

  • A broad class of effective learning rules are shown to be natural gradient descent.
  • Parameter updates are demonstrated to be a product of a positive-definite matrix and a loss gradient.
  • The framework applies to continuous-time, discrete-time, stochastic, and higher-order learning rules.

Conclusions:

  • The gradient is a fundamental object underlying all learning processes.
  • This work provides a unified theoretical framework for understanding learning.
  • The findings have practical implications for artificial intelligence, control systems, and experimental neuroscience.