Abstract
The present work describes an improved version of MART (Multichannel ART), a neural network aimed at the adaptive recognition of multichannel patterns. As is habitual in ART networks, MART is directed at problems that require unsupervised learning, but it has a greater level of adaptability to the characteristics of the input patterns, selectively evaluating the different signal channels on which it operates and the classes learnt, modulating the discrimination capacity, and dynamically learning/forgetting classes with regard to their level of representativity.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Barro, S., Fernández-Delgado, M., Vila, J.A., Regueiro, C.V. and Sánchez, E.: An adaptive neural network for the classification of electrocardiographic patterns on multichannel ECG. IEEE Engineering in Medicine and Biology Magazine. Vol. 17, 1, (1998) 139–150.
Carpenter G.A. and Grossberg S.: ART2: Self-organizing of stable category recognition codes for analog input patters. Applied Optics, Vol. 16, 23, (1987).
Carpenter G.A. and Grossberg S.: The ART of adaptive pattern recognition by a self-organizing neural network. Computer, Vol. 21, 3, (1988) 77–87.
Fernández-Delgado M. and Barro S.: MART: A multichannel ART-based neural network. IEEE Transactions in Neural Networks, Vol. 9, 1, (1988) 139–150.
Nigrin A.: Neural Networks for pattern recognition. The MIT Press, (1993) 20–34, ISBN 0-262-14054-3.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1999 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fernández-Delgado, M., Presedo, J., Barro, S. (1999). Multichannel pattern recognition neural network. In: Mira, J., Sánchez-Andrés, J.V. (eds) Foundations and Tools for Neural Modeling. IWANN 1999. Lecture Notes in Computer Science, vol 1606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0098230
Download citation
DOI: https://doi.org/10.1007/BFb0098230
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-66069-9
Online ISBN: 978-3-540-48771-5
eBook Packages: Springer Book Archive