Yprel nets and classification
| Autor: | A. Ennaji, P. Chavy, F. Gilles, Y. Lecourtier |
|---|---|
| Rok vydání: | 2002 |
| Předmět: |
Learning vector quantization
Artificial neural network Contextual image classification Computer science business.industry Pattern recognition Linear classifier Semi-supervised learning Multilayer perceptron Feature (machine learning) One-class classification Unsupervised learning Artificial intelligence business |
| Zdroj: | Proceedings of IEEE Systems Man and Cybernetics Conference - SMC. |
| DOI: | 10.1109/icsmc.1993.385055 |
| Popis: | In this paper we present a scheme of classification based on a particular processing element ("neuron") called Yprel. The main characteristics of the approach are: (1) a Yprel classifier is a set of Yprel nets, each net being associated to a particular class; (2) the learning is supervised and conducted class by class; (3) the structure of the net is not a priori chosen, but is determined step by step during the learning process; and (4) partial re-learning and/or co-operation between nets can be added to improve the results. Preliminary results are given on a well-known classification task (recognition of typographic characters). > |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|