Interestingness Indices for Building Neural Networks Based on Concept Lattice-Reference-Cited by-同舟云学术

Interestingness Indices for Building Neural Networks Based on Concept Lattice

Published:2024-03 Issue:3 Volume:85 Page:
ISSN:0005-1179
Container-title:Automation and Remote Control
language:
Short-container-title:ARC

Author:

,Zueva M. M.,Kuznetsov S. O.,

Abstract

The difficulty of interpreting performance of neural networks is a well-known problem, which is attracting a lot of attention. In particular, neural networks based on concept lattices present a promising direction in this area. Selection of formal concepts for building a neural network has a key effect on the quality of its performance. Criteria for selecting formal concepts can be based on interestingness indices, when concepts with the highest values of a certain index are used to build a neural network. This article studies the influence of the choice of an interestingness index on the neural network performance.

Publisher

The Russian Academy of Sciences

Reference10 articles.

1. 1. Norbert Tsopze, Engelbert Mephu Nguifo, and Gilbert Tindo, CLANN: Concept Lattice-Based Artificial Neural Network for Supervised Classification, in The Fifth International Conference on Concept Lattices and Their Applications, 2007, pp. 24-26.

2. 2. Kuznetsov, S.O., Makhazhanov, N., and Ushakov, M., On Neural Network Architecture Based on Concept Lattices, ISMIS 2017, 2017, pp. 653-663.

3. 3. Kuznetsov, S.O. and Makhalova, T.P., Concept Interestingness Measures: A Comparative Study, Proceedings of the Twelfth International Conference on Concept Lattices and Their Applications, 2015, pp. 59-72.

4. 4. Kuznetsov, S.O. and Makhalova, T.P., On Interestingness Measures of Formal Concepts, Inf. Sci., 2017.

5. 5. Ganter, B. and Wille, R., Contextual Attribute Logic, in Conceptual Structures: Standards and Practices, Lecture Notes in Computer Science. 1640, Tepfenhart, W.M. and Cyre, W., Eds., Berlin-Heidelberg: Springer, 1999, pp. 377-388.