Extracting reducible knowledge from ANN with JBOS and FCANN approaches

Authors:
SéRgio M. Dias;Luis E. ZáRate;Newton J. Vieira
Affiliations:
Department of Computer Science, Federal University of Minas Gerais (UFMG), Av. Antônio Carlos 6627-ICEx, 4010 Pampulha, 31.270-010 Belo Horizonte, Minas Gerais, Brazil and Technology Strategi ...;Department of Computer Science, Pontifical Catholic University of Minas Gerais (PUC Minas), Av. Dom José Gaspar 500, 30.535-610 Belo Horizonte, Minas Gerais, Brazil;Department of Computer Science, Federal University of Minas Gerais (UFMG), Av. Antônio Carlos 6627-ICEx, 4010 Pampulha, 31.270-010 Belo Horizonte, Minas Gerais, Brazil
Venue:
Expert Systems with Applications: An International Journal
Year:
2013

Citing 12
Cited 0

Extracting Refined Rules from Knowledge-Based Neural Networks

Machine Learning
Formal Concept Analysis: Mathematical Foundations

Formal Concept Analysis: Mathematical Foundations
Computing iceberg concept lattices with TITANIC

Data & Knowledge Engineering
Concept Data Analysis: Theory and Applications

Concept Data Analysis: Theory and Applications
Complexity Reduction in Lattice-Based Information Retrieval

Information Retrieval
A robust neural networks approach for spatial and intensity-dependent normalization of cDNA microarray data

Bioinformatics
FCANN: A new approach for extraction and representation of knowledge from ANN trained via Formal Concept Analysis

Neurocomputing
Qualitative behavior rules for the cold rolling process extracted from trained ANN via the FCANN method

Engineering Applications of Artificial Intelligence
Formal concept analysis with background knowledge: attribute priorities

IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews - Special issue on information reuse and integration
Refinement of approximate domain theories by knowledge-based neural networks

AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 2
Are artificial neural networks black boxes?

IEEE Transactions on Neural Networks
Applying the JBOS reduction method for relevant knowledge extraction

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

Due to its ability to handle nonlinear problems, artificial neural networks are applied in several areas of science. However, the human elements are unable to assimilate the knowledge kept in those networks, since such knowledge is implicitly represented by their connections and the respective numerical weights. In recent formal concept analysis, through the FCANN method, it has demonstrated a powerful methodology for extracting knowledge from neural networks. However, depending on the settings used or the number of the neural network variables, the number of formal concepts and consequently of rules extracted from the network can make the process of knowledge and learning extraction impossible. Thus, this paper addresses the application of the JBOS approach to extracted reduced knowledge from the formal contexts extracted by FCANN from the neural network. Thus, providing a small number of formal concepts and rules for the final user, without losing the ability to understand the process learned by the network.