Extracting rules from trained neural networks

Authors:
H. Tsukimoto
Affiliations:
Res. & Dev. Center, Toshiba Corp., Kawasaki
Venue:
IEEE Transactions on Neural Networks
Year:
2000

Citing 0
Cited 22

Knowledge Discovery from fMRI Brain Images by Logical Regression Analysis

DS '00 Proceedings of the Third International Conference on Discovery Science
Rule Discovery from fMRI Brain Images by Logical Regression Analysis

Progress in Discovery Science, Final Report of the Japanese Discovery Science Project
Extraction of Logical Rules from Data by Means of Piecewise-Linear Neural Networks

DS '02 Proceedings of the 5th International Conference on Discovery Science
Growing neural network trees efficiently and effectively

Design and application of hybrid intelligent systems
Fuzzy rule extraction from a feed forward neural network by training a representative fuzzy neural network using gradient descent

International Journal of Uncertainty, Fuzziness and Knowledge-Based Systems
Piecewise-Linear Neural Networks and Their Relationship to Rule Extraction from Data

Neural Computation
Compiled code simulation of analog and mixed-signal systems using piecewise linear modeling of nonlinear parameters: A case study for ΔΣ modulator simulation

Integration, the VLSI Journal
Extracting linguistic quantitative rules from supervised neural networks

International Journal of Knowledge-based and Intelligent Engineering Systems
Efficient design of neural network tree using a new splitting criterion

Neurocomputing
Greedy rule generation from discrete data and its use in neural network rule extraction

Neural Networks
Data mining for the diagnosis of type II diabetes from three-dimensional body surface anthropometrical scanning data

Computers & Mathematics with Applications
Measures of Ruleset Quality Capable to Represent Uncertain Validity

ECSQARU '07 Proceedings of the 9th European Conference on Symbolic and Quantitative Approaches to Reasoning with Uncertainty
Measures of ruleset quality for general rules extraction methods

International Journal of Approximate Reasoning
Transaction-item association matrix-based frequent pattern network mining algorithm in large-scale transaction database

WSEAS Transactions on Computers
Fault detection and fuzzy rule extraction in AC motors by a neuro-fuzzy ART-based system

Engineering Applications of Artificial Intelligence
Analysis of artificial neural network learning near temporary minima: A fuzzy logic approach

Fuzzy Sets and Systems
Outlier identify based on BP neural network in dam safety monitoring

CAR'10 Proceedings of the 2nd international Asia conference on Informatics in control, automation and robotics - Volume 2
A unified approach to the extraction of rules from artificial neural networks and support vector machines

ADMA'10 Proceedings of the 6th international conference on Advanced data mining and applications - Volume Part II
Reverse Engineering the Neural Networks for Rule Extraction in Classification Problems

Neural Processing Letters
Knowledge-based approach to septic shock patient data using a neural network with trapezoidal activation functions

Artificial Intelligence in Medicine
Rules extraction from constructively trained neural networks based on genetic algorithms

Neurocomputing
Prediction of the Amount of Wood Using Neural Networks

Journal of Mathematical Modelling and Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

Presents an algorithm for extracting rules from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural network whose output function is monotone such as a sigmoid function. Therefore, the algorithm can be applied to multilayer neural networks, recurrent neural networks and so on. It does not depend on training algorithms, and its computational complexity is polynomial. The basic idea is that the units of neural networks are approximated by Boolean functions. But the computational complexity of the approximation is exponential, and so a polynomial algorithm is presented. The author has applied the algorithm to several problems to extract understandable and accurate rules. The paper shows the results for the votes data, mushroom data, and others. The algorithm is extended to the continuous domain, where extracted rules are continuous Boolean functions. Roughly speaking, the representation by continuous Boolean functions means the representation using conjunction, disjunction, direct proportion, and reverse proportion. This paper shows the results for iris data