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

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...

Reinforcement Schedules

Reinforcement Schedules

Positive reinforcement is a powerful method for teaching new behaviors to both animals and humans. B.F. Skinner demonstrated this with his experiments using rats in a Skinner box. When a rat pressed a lever, it received a food pellet. This immediate reward encouraged the rat to repeat the behavior. This method, where a reward follows every instance of the behavior, is known as continuous reinforcement. It is highly effective for establishing new behaviors quickly.
Once a behavior is learned,...

Reinforcement

Reinforcement

Positive and negative reinforcement are key concepts in operant conditioning, a learning process where the consequences of a behavior affect the likelihood of that behavior being repeated.
Positive reinforcement occurs when a behavior is followed by the presentation of a rewarding stimulus, increasing the frequency of that behavior. For example:

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...

Machines: Problem Solving II

Machines: Problem Solving II

Machines are complex structures consisting of movable, pin-connected multi-force members that work together to transmit forces. Consider a lifting tong carrying a 100 kg load. It comprises movable sections DAF and CBG linked together with member AB.

Ampere-Maxwell's Law: Problem-Solving

Ampere-Maxwell's Law: Problem-Solving

A parallel-plate capacitor with capacitance C, whose plates have area A and separation distance d, is connected to a resistor R and a battery of voltage V. The current starts to flow at t = 0. What is the displacement current between the capacitor plates at time t? From the properties of the capacitor, what is the corresponding real current?
To solve the problem, we can use the equations from the analysis of an RC circuit and Maxwell's version of Ampère's law.
For the first part of...

You might also read

Related Articles

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

Sort by

Same author

Standardized surgical access to the porcine temporomandibular joint: Anatomical basis for translational research.

Laboratory animals·2026

Same author

Accelerating scientific discovery with Co-Scientist.

Nature·2026

Same author

Pseudo-сolloidal species of actinides in contaminated aquifers. Insights from experimental and modeling approaches.

Journal of contaminant hydrology·2026

Same author

Advancing conversational diagnostic AI with multimodal reasoning.

Nature medicine·2026

Same author

<i>NKX6.1</i> mRNA copy number is an actionable biomarker associated with islet function and clinical outcomes after islet transplantation.

Science translational medicine·2026

Same author

Advancing regulatory variant effect prediction with AlphaGenome.

Nature·2026

Same journal

Retraction Note: NSD2 targeting reverses plasticity and drug resistance in prostate cancer.

Nature·2026

Same journal

Enhanced B cell priming induces broadly neutralizing HIV-1 apex antibodies.

Nature·2026

Same journal

Vaccination elicits HIV broadly neutralizing antibodies in primates.

Nature·2026

Same journal

Child online safety needs more than social-media bans.

Nature·2026

Same journal

Ebola preparedness must start with ecosystems and before humans show symptoms.

Nature·2026

Same journal

AI tools can speed up thinking, but evidence still comes from the lab bench.

Nature·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 26, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Discovering faster matrix multiplication algorithms with reinforcement learning.

Alhussein Fawzi¹, Matej Balog², Aja Huang²

¹DeepMind, London, UK. afawzi@deepmind.com.

|October 5, 2022

Summary

This summary is machine-generated.

Deep reinforcement learning, via AlphaTensor, discovers new matrix multiplication algorithms. This AI approach significantly improves computational efficiency, outperforming human-designed methods for key matrix sizes.

More Related Videos

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Related Experiment Videos

Last Updated: Aug 26, 2025

Deep Neural Networks for Image-Based Dietary Assessment

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Behavioral Training Procedures for Head-fixed Virtual Reality in Mice

Published on: September 6, 2024

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Investigating Motor Skill Learning Processes with a Robotic Manipulandum

Published on: February 12, 2017

Area of Science:

Computer Science
Artificial Intelligence
Computational Mathematics

Background:

Matrix multiplication is a fundamental computation impacting diverse fields like neural networks and scientific computing.
Discovering novel algorithms for matrix multiplication is challenging due to the vast search space.
Existing algorithms, while efficient, may not represent the optimal solution.

Purpose of the Study:

To develop an AI-driven approach for discovering efficient and provably correct matrix multiplication algorithms.
To explore the potential of deep reinforcement learning in automating algorithmic discovery.
To achieve breakthroughs in matrix multiplication complexity beyond human intuition.

Main Methods:

Utilized a deep reinforcement learning agent, AlphaTensor, inspired by AlphaZero.
Trained AlphaTensor to play a game focused on finding tensor decompositions within a finite factor space.
Applied the agent to discover algorithms for arbitrary and structured matrix multiplication.

Main Results:

AlphaTensor discovered algorithms that surpass state-of-the-art complexity for various matrix dimensions.
A novel algorithm for 4x4 matrices in a finite field improves upon Strassen's 50-year-old method.
Demonstrated optimization for specific hardware runtimes and structured matrix multiplication.

Conclusions:

Deep reinforcement learning, exemplified by AlphaTensor, can accelerate algorithmic discovery.
The approach offers a pathway to surpassing human-designed algorithms for fundamental computational tasks.
AlphaTensor provides a flexible framework for optimizing algorithms based on different criteria, including computational complexity and practical efficiency.