Knowledge-based fuzzy MLP for classification and rule generation

Authors:
S. Mitra;R. K. De;S. K. Pal
Affiliations:
Machine Intelligence Unit, Indian Stat. Inst., Calcutta;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1997

Citing 0
Cited 8

Trading off between Misclassification, Recognition and Generalization in Data Mining with Continuous Features

IEA/AIE '02 Proceedings of the 15th international conference on Industrial and engineering applications of artificial intelligence and expert systems: developments in applied artificial intelligence
Extraction of Logical Rules from Data by Means of Piecewise-Linear Neural Networks

DS '02 Proceedings of the 5th International Conference on Discovery Science
Piecewise-Linear Neural Networks and Their Relationship to Rule Extraction from Data

Neural Computation
Fuzzy neural network models for multispectral image analysis

CSECS'06 Proceedings of the 5th WSEAS International Conference on Circuits, Systems, Electronics, Control & Signal Processing
Improving the performance of resource allocation networks through hierarchical clustering of high-dimensional data

ICANN/ICONIP'03 Proceedings of the 2003 joint international conference on Artificial neural networks and neural information processing
Development of an adaptive neuro-fuzzy classifier using linguistic hedges: Part 1

Expert Systems with Applications: An International Journal
Computational theory perception (CTP), rough-fuzzy uncertainty analysis and mining in bioinformatics and web intelligence: a unified framework

Transactions on Rough Sets XI
Fuzzy-Rule Based Adaptive Data Warehouse: An Extension of Data Warehouse as Knowledge Warehouse

International Journal of Applied Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new scheme of knowledge-based classification and rule generation using a fuzzy multilayer perceptron (MLP) is proposed. Knowledge collected from a data set is initially encoded among the connection weights in terms of class a priori probabilities. This encoding also includes incorporation of hidden nodes corresponding to both the pattern classes and their complementary regions. The network architecture, in terms of both links and nodes, is then refined during training. Node growing and link pruning are also resorted to. Rules are generated from the trained network using the input, output, and connection weights in order to justify any decision(s) reached. Negative rules corresponding to a pattern not belonging to a class can also be obtained. These are useful for inferencing in ambiguous cases. Results on real life and synthetic data demonstrate that the speed of learning and classification performance of the proposed scheme are better than that obtained with the fuzzy and conventional versions of the MLP (involving no initial knowledge encoding). Both convex and concave decision regions are considered in the process