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

Cognitive Learning

Cognitive Learning

Cognitive learning is based on purposive behavior, incidental learning, and insight learning.
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...

Wheatstone Bridge

Wheatstone Bridge

An ohmmeter is a resistance-measuring device. It works by applying a voltage to a resistor of unknown resistance and measuring the current across the resistor. The resistance value is deduced using Ohm's law. Usually, the standard configuration of an ohmmeter comprises a voltmeter or an ammeter. However, such configurations are limited in accuracy because the meters alter the voltage applied to the resistor and the current that flows through it.
Thus, for accurate resistance measurements, a...

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.

Principle of Virtual Work: Problem Solving

Principle of Virtual Work: Problem Solving

The principle of virtual work is an essential concept in the field of mechanics and engineering. This is used to solve problems related to the equilibrium of a structure or system. It is based on the assumption that if a system is in equilibrium, the work done by all the forces during a virtual displacement is zero. This principle is applied by considering virtual displacements of the system and the corresponding work done by internal and external forces.
To apply the principle of virtual work,...

Avoidance Learning and Learned Helplessness

Avoidance Learning and Learned Helplessness

Avoidance learning and learned helplessness are critical concepts in understanding behavioral responses to negative stimuli.
Avoidance learning occurs when an organism learns that a specific behavior can prevent an unpleasant outcome. For example, a student who receives a bad grade may start studying harder to avoid future poor grades. This behavior persists even when the negative outcome is no longer present. Avoidance learning is powerful because it maintains behavior in the absence of the...

Statically Indeterminate Problem Solving

Statically Indeterminate Problem Solving

Statically indeterminate problems are those where statics alone can not determine the internal forces or reactions. Consider a structure comprising two cylindrical rods made of steel and brass. These rods are joined at point B and restrained by rigid supports at points A and C. Now, the reactions at points A and C and the deflection at point B are to be determined. This rod structure is classified as statically indeterminate as the structure has more supports than are necessary for maintaining...

You might also read

Related Articles

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

Sort by

Same author

Interpretable inverse iteration mean shift networks for clustering tasks.

Neural networks : the official journal of the International Neural Network Society·2025

Same author

Unsupervised Feature Selection for High-Order Embedding Learning and Sparse Learning.

IEEE transactions on cybernetics·2025

Same author

Leveraging spiking neural networks for topic modeling.

Neural networks : the official journal of the International Neural Network Society·2024

Same author

Multi-Label Contrastive Learning for Abstract Visual Reasoning.

IEEE transactions on neural networks and learning systems·2022

Same author

Spike-Timing-Dependent Plasticity With Activation-Dependent Scaling for Receptive Fields Development.

IEEE transactions on neural networks and learning systems·2021

Same author

Recent Advances in General Game Playing.

TheScientificWorldJournal·2015

Search research articles

Related Experiment Video

Updated: Jun 26, 2026

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

Learning without human expertise: a case study of the double dummy bridge problem.

Krzysztof Mossakowski¹, Jacek Mańdziuk

¹Faculty of Mathematics and Information Science, Warsaw University of Technology, 00-661 Warsaw, Poland. mossakow@mini.pw.edu.pl

IEEE Transactions on Neural Networks

|January 20, 2009

Summary

Artificial neural networks trained on bridge deals accurately predict trick outcomes, outperforming human experts. The networks learned game strategies without explicit human knowledge, revealing patterns similar to experienced players.

Related Experiment Videos

Last Updated: Jun 26, 2026

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

The Double-H Maze: A Robust Behavioral Test for Learning and Memory in Rodents

Published on: July 8, 2015

Area of Science:

Artificial Intelligence
Machine Learning
Computational Game Theory

Background:

The double dummy bridge problem (DDBP) is a complex card game scenario.
Estimating trick outcomes in DDBP typically requires human expertise or complex algorithms.
Previous research has explored AI for game strategy but with limited success in complex games like bridge.

Purpose of the Study:

To evaluate artificial neural networks (ANNs) for solving the double dummy bridge problem (DDBP).
To compare ANNs trained solely on game data against those incorporating human knowledge.
To analyze learned patterns within ANNs for insights into human bridge strategies.

Main Methods:

Developed and tested four ANN architectures with different data representations for DDBP.
Trained ANNs exclusively on sample bridge deals, without explicit game rules or human input.
Compared ANN performance against 24 professional human bridge players on test datasets.

Main Results:

The best-performing ANN, trained solely on sample deals, surpassed all other architectures, including those using human knowledge.
This superior network achieved perfect trick predictions in 53.11% of suit contracts and 37.80% of notrump contracts.
ANN performance was comparable or superior to professional human players, with discovered weight patterns mirroring human strategies.

Conclusions:

ANNs can effectively learn complex game strategies, like those in DDBP, from data alone.
This approach offers a powerful method for solving complex problems and potentially discovering new strategies.
The study demonstrates the potential of AI in understanding and replicating human expertise in strategic domains.