This paper describes the recognition of image patterns based on novel representation learning techniques by considering higher-level (meta-)representations of numerical data in a mathematical lattice. In particular, the interest here focuses on lattices of (Type-1) Intervals’ Numbers (INs), where an IN represents a distribution of image features including orthogonal moments. A neural classifier, namely fuzzy lattice reasoning (flr) fuzzy-ARTMAP (FAM), or flrFAM for short, is described for learning distributions of INs; hence, Type-2 INs emerge. Four benchmark image pattern recognition applications are demonstrated. The results obtained by the proposed techniques compare well with the results obtained by alternative methods from the literature. Furthermore, due to the isomorphism between the lattice of INs and the lattice of fuzzy numbers, the proposed techniques are straightforward applicable to Type-1 and/or Type-2 fuzzy systems. The far-reaching potential for deep learning in big data applications is also discussed.
V.G. Kaburlasos, G.A. Papakostas, “Learning distributions of image features by interactive fuzzy lattice reasoning (FLR) in pattern recognition applications”, IEEE Computational Intelligence Magazine, vol. 10, no. 3, pp. 42–51, 2015 (Special Issue on New Trends of Learning in Computational Intelligence. Guest Editors: Guang-Bin Huang, Erik Cambria, Kar-Ann Toh, Bernard Widrow, Zongben Xu).