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

Rules for Defining Functions

Rules for Defining Functions

A relation is a function if each input x is associated with exactly one output y. For example, the equation y = 2x + 5 defines a function because every value of x yields a unique y. However, x = y² + 1 is not a function of x, since a single x-value, such as x = 2, corresponds to two possible y-values: y = 1 and y = -1.The vertical line test helps determine whether a graph represents a function. If a vertical line intersects a curve more than once, the curve fails the test and does not...

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Woodward–Hoffmann Selection Rules and Microscopic Reversibility

Electrocyclic reactions, cycloadditions, and sigmatropic rearrangements are concerted pericyclic reactions that proceed via a cyclic transition state. These reactions are stereospecific and regioselective. The stereochemistry of the products depends on the symmetry characteristics of the interacting orbitals and the reaction conditions. Accordingly, pericyclic reactions are classified as either symmetry-allowed or symmetry-forbidden. Woodward and Hoffmann presented the selection criteria for...

Neural Regulation

Neural Regulation

Digestion begins with a cephalic phase that prepares the digestive system to receive food. When our brain processes visual or olfactory information about food, it triggers impulses in the cranial nerves innervating the salivary glands and stomach to prepare for food.

Neural Circuits

Neural Circuits

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...

Neuroplasticity

Neuroplasticity

Neuroplasticity reflects the brain's remarkable capacity to adapt and evolve, responding dynamically to learning, experiences, or injury by reorganizing its neural circuitry. This reorganization involves creating new neural connections and refining old ones through a series of biological processes that contribute to the brain's lifelong development and adaptability.

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...

You might also read

Related Articles

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

Sort by

Same author

Deep kernel learning enhanced fusion for multimodal classification.

Neural networks : the official journal of the International Neural Network Society·2026

Same author

A novel modality contribution confidence-enhanced multimodal deep learning framework for multiomics data.

BMC bioinformatics·2025

Same author

Semi-supervised deep matrix factorization model for clustering multi-omics data.

Computer methods and programs in biomedicine·2025

Same author

Recent Advances in Food Drying Modeling: Empirical to Multiscale Physics-Informed Neural Networks.

Comprehensive reviews in food science and food safety·2025

Same author

Pre-gating and contextual attention gate - A new fusion method for multi-modal data tasks.

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

Same author

A review on modelling of thermochemical processing of biomass for biofuels and prospects of artificial intelligence-enhanced approaches.

Bioresource technology·2023

Search research articles

Related Experiment Videos

Generating rules with predicates, terms and variables from the pruned neural networks.

¹Faculty of Information Technology, Queensland University of Technology, S 537 Gardens Point, GPO Box 2434, Brisbane, QLD 4001, Australia. r.nayak@qut.edu.au

Neural Networks : the Official Journal of the International Neural Network Society

|March 10, 2009

Summary

This study introduces Gyan, a new method to represent artificial neural network (ANN) knowledge using first-order predicate rules. Gyan enhances understanding of ANN behavior while preserving accuracy.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Knowledge Representation

Background:

Artificial neural networks (ANNs) excel in prediction but struggle with transparent knowledge representation.
ANNs lack succinct methods for representing their internal reasoning processes.
Existing methods often sacrifice interpretability for predictive power.

Purpose of the Study:

To propose a novel methodology, Gyan, for representing ANN knowledge.
To convert trained ANN knowledge into restricted first-order predicate rules.
To improve the comprehensibility of ANN models without losing accuracy.

Main Methods:

Developing the Gyan methodology for knowledge extraction from ANNs.
Training an ANN and applying Gyan to derive symbolic rules.
Comparing the derived rules with propositional rules for accuracy and fidelity.

Main Results:

Gyan successfully represents trained ANN knowledge as first-order predicate rules.
The derived symbolic rules offer improved comprehensibility of ANN behavior.
The methodology maintains the accuracy and fidelity of the original propositional rules.

Conclusions:

Gyan provides a viable approach for symbolic knowledge representation of ANNs.
This method enhances the interpretability of complex neural networks.
Gyan bridges the gap between connectionist and symbolic AI.