Search. Read. Cite.

Easy to search. Easy to read. Easy to cite with credible sources.

Research Article
Explaining Results of Artificial Neural Networks

D. Yedjour, H. Yedjour and A. Benyettou

Journal of Applied Sciences, 2011, 11(15), 2855-2860.

Abstract

Neural networks are very efficient in solving various problems but they have no ability of explaining their answers and presenting gathered knowledge in a comprehensible way. Two main approaches are used, namely the pedagogical one that treats a network as a black box and the local one that examines its structure. Because searching rules is similar to NP-hard problem it justifies an application of evolutionary algorithm to the rule extraction. Pedagogical approaches such as GA are insensitive to the number of units of neural networks as they see them as "black boxes" interested only their inputs and their outputs. In the study we describe new rule extraction method based on evolutionary algorithm called GenRGA. It uses logical rules and is composed of three (03) main parts: genetic module, neural networks module and rules simplification module. GenRGA is tested in experimental studies using different benchmark data sets from UCI repository. Comparisons with other methods show that the extracted rules are accurate and highly comprehensible.

ASCI-ID: 35-4253

Cited References Fulltext

Related Articles


Object Recognition Using ANN with Backpropogation Algorithm

Journal of Applied Sciences, 2002, 2(3), 281-287.

Application of Moving Object Tracking Based on Kalman Filter Algorithm

Journal of Applied Sciences, 2013, 13(19), 4096-4098.

Algorithm of Comprehensive Evaluation of Quality on Marketing Simulation Practice Based on FAHP

Journal of Applied Sciences, 2013, 13(4), 627-632.

Mixture Density Estimation Clustering Based Probabilistic Neural Network Variants for Multiple Source Partial Discharge Signature Analysis

Journal of Applied Sciences, 2014, 14(14), 1496-1505.

Non-stationary 1D Thin Bed Model for Non-stationary Frequency Bandwidth Expansion Algorithms

Journal of Applied Sciences, 2014, 14(7), 651-659.

Improvement of Remote Sensing Techniques in TPW Assessment Using Radiosonde Data

Journal of Applied Sciences, 2008, 8(3), 480-488.

Cited By


Combination Neural Network and Financial Indices for Stock Price Prediction

Journal of Applied Sciences, 2011, 11(19), 3429. DOI: 10.3923/jas.2011.3429.3435

Machine Learning Data Imputation and Classification in a Multicohort Hypertension Clinical Study

Bioinformatics and Biology Insights, 2015, 9s3(), BBI.S29473. DOI: 10.4137/BBI.S29473