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

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...

Classification of Neurotransmitters

Classification of Neurotransmitters

Neurotransmitters play a crucial role in the communication between neurons in the autonomic nervous system. Neurons in the autonomic nervous system can be cholinergic or adrenergic depending on the neurotransmitters synthesized. Cholinergic neurons use acetylcholine as their primary neurotransmitter. This includes all the preganglionic fibers of the sympathetic and pre- and postganglionic fibers of the parasympathetic nervous systems. In addition, neurons of the somatic nervous system also use...

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...

You might also read

Related Articles

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

Sort by

Same author

TAVR--A new way to treat ventricular storm and ventricular fibrillation.

International journal of cardiology·2016

Same author

Fishing in the left atrium: A nightmare.

International journal of cardiology·2015

Same author

High rates of prasugrel and ticagrelor non-responder in patients treated with therapeutic hypothermia after cardiac arrest.

Resuscitation·2014

Same author

Regulation of glucose-6-phosphatase gene expression by insulin and metformin.

Hormone and metabolic research = Hormon- und Stoffwechselforschung = Hormones et metabolisme·2009

Same author

A connectionist approach to generating oblique decision trees.

IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society·2008

Same author

Extracting M-of-N rules from trained neural networks.

IEEE transactions on neural networks·2008

Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013

Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011

Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011

Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011

Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011

Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011

See all related articles

Search research articles

Related Experiment Videos

Recursive neural network rule extraction for data with mixed attributes.

R Setiono¹, B Baesens, C Mues

¹School of Computing, National University of Singapore, Singapore 117543, Republic of Singapore. rudys@comp.nus.edu.sg

IEEE Transactions on Neural Networks

|February 14, 2008

Summary

This summary is machine-generated.

This study introduces a novel recursive algorithm for extracting classification rules from neural networks (NNs). The method generates more accurate and understandable rules for datasets with mixed attributes, improving upon existing NN rule extraction techniques.

Related Experiment Videos

Area of Science:

Artificial Intelligence
Machine Learning
Data Mining

Background:

Neural networks (NNs) are powerful tools for classification but often lack interpretability.
Extracting understandable rules from NNs trained on complex datasets is challenging.
Existing rule extraction methods may struggle with datasets containing both discrete and continuous attributes.

Purpose of the Study:

To develop a recursive algorithm for extracting classification rules from feedforward neural networks (NNs).
To address the challenge of rule extraction from datasets with mixed discrete and continuous attributes.
To generate rules that are both accurate and comprehensible.

Main Methods:

A recursive algorithm is proposed for rule extraction from feedforward neural networks.
The algorithm generates rules with disjoint conditions for discrete and continuous attributes.
It starts with discrete attributes and refines rules using continuous attributes (hyperplanes) when necessary.

Main Results:

The algorithm successfully extracts classification rules from NNs trained on mixed-attribute datasets.
Extracted rules demonstrate improved accuracy compared to existing methods.
The generated rules are more comprehensible, aiding in understanding the NN's classification process.

Conclusions:

The proposed recursive algorithm offers a superior approach to NN rule extraction for mixed-attribute data.
The disjoint attribute condition in rules enhances interpretability.
This method provides a valuable tool for explaining complex neural network decisions in practical applications like credit scoring.