Abstract
Morphological neural networks, in particular, those with dendritic processing (MNNDPs), have shown to be a very promising tool for pattern classification. In this chapter, we present a survey of the most recent advances concerning MNNDPs. We provide the basics of each model and training algorithm; in some cases, we present simple examples to facilitate the understanding of the material. In all cases, we compare the described models with some of the state-of-the-art counterparts to demonstrate the advantages and disadvantages. In the end, we present a summary and a series of conclusions and trends for present and further research.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Arce, F., Zamora, E., Sossa, H., & Barrón, R. (2016). Dendrite morphological neural networks trained by differential evolution. In Proceedings of 2016 IEEE Symposium Series on Computational Intelligence (SSCI), Athens, Greece (vol. 1, pp. 1–8).
Arce, F., Zamora, E., Sossa, H., & Barrón, R. (2017). Differential evolution training algorithm for dendrite morphological neural networks. Under Review in Applied Soft Computing.
Ardia, D., Boudt, K., Carl, P., Mullen, K., & Peterson, B. (2011). Differential evolution with DEoptim: An application to non-convex portfolio optimization. The R Journal, 3(1), 27–34.
Asuncion, D. (2007). UCI machine learning repository. [online] Available at: http://archive.ics.uci.edu/ml/index.php.
Barmpoutis, A., & Ritter, G. (2006). Orthonormal basis lattice neural networks. In Proceedings of the IEEE International Conference on Fuzzy Systems, Vancouver, British Columbia, Canada (vol. 1, pp. 331–336).
Broomhead, D., & Lowe, D. (1988a). Radial basis functions, multi-variable functional interpolation and adaptive networks. (Technical Report). RSRE. 4148.
Broomhead, D., & Lowe, D. (1988b). Multivariable functional interpolation and adaptive networks. Complex Systems, 2(3), 321–355.
Cortes, C., & Vapnik, V. (1995). Support vector networks. Machine Learning, 20(3), 273–297.
Guevara, E. (2016). Method for training morphological neural networks with dendritic processing. Ph.D. Thesis. Center for Computing Research. National Polytechnic Institute.
Guang, G., Zhu, Q., & Siew, Ch. (2006). Extreme learning machine: theory and applications. Neurocomputing, 70(1–3), 489–501.
Huang, G., Huang, G., Song, S., & You, K. (2015). Trends in extreme learning machines: A review. Neural Networks, 61, 32–48.
McCulloch, W., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics, 5, 115–133.
Ojeda, L., Vega, R., Falcon, L., Sanchez-Ante, G., Sossa, H., & Antelis, J. (2015). Classification of hand movements from non-invasive brain signals using lattice neural networks with dendritic processing. In Proceedings of the 7th Mexican Conference on Pattern Recognition (MCPR) LNCS 9116, Springer Verlag (pp. 23–32).
Ritter, G., & Beaver, T. (1999). Morphological perceptrons. In Proceedings of the International Joint Conference on Neural Networks (IJCNN). Washington, DC, USA (vol. 1, pp. 605–610).
Ritter, G., Iancu, L., & Urcid, G. (2003). Morphological perceptrons with dendritic structure. In Proceedings of the 12th IEEE International Conference in Fuzzy Systems (FUZZ), Saint Louis, Missouri, USA (vol. 2, pp. 1296–1301).
Ritter, G., & Schmalz, M. (2006). Learning in lattice neural networks that employ dendritic computing. In Proceedings of the 2006 IEEE International Conference on Fuzzy Systems(FUZZ), Vancouver, British Columbia, Canada (vol. 1, pp. 7–13).
Ritter, G., & Urcid, G. (2007). Learning in lattice neural networks that employ dendritic computing. Computational Intelligence Based on Lattice Theory, 67, 25–44.
Ritter, G., Urcid, G., & Valdiviezo, J. (2014). Two lattice metrics dendritic computing for pattern recognition. In Proceedings of the 2014 IEEE International Conference on Fuzzy Systems (FUZZ), Beijing, China (pp. 45–52).
Rosenblatt, F. (1958). The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review, 65(6), 386–408.
Rosenblatt, F. (1962). Principles of neurodynamics: Perceptron and theory of brain mechanisms (1st ed.). Washington, DC, USA: Spartan Books.
Sossa, H., & Guevara, E. (2013a). Modified dendrite morphological neural network applied to 3D object recognition. In Proceedings of the Mexican Conference on Pattern Recognition (MCPR), LNCS (vol. 7914, pp. 314–324).
Sossa, H., & Guevara, E. (2013b). Modified dendrite morphological neural network applied to 3D object recognition on RGB-D data. In Proceedings of the 8th International Conference on Hybrid Artificial Intelligence Systems (HAIS), LNAI (vol. 8073, pp. 304–313).
Sossa, H., & Guevara, E. (2014). Efficient training for dendrite morphological neural networks. Neurocomputing, 131, 132–142.
Sossa, H., Cortés, G., & Guevara, E. (2014). New radial basis function neural network architecture for pattern classification: First results. In Proceedings of the 19th Iberoamerican Congress on Pattern Recognition (CIARP), Puerto Vallarta, México, LNCS (vol. 8827, pp. 706–713).
Sussner, P., & Esmi, E., (2009). An introduction to morphological perceptrons with competitive learning. In Proceedings of the 2009 International Joint Conference on Neural Networks (IJCNN), Atlanta, Georgia, USA (pp. 3024–3031).
Sussner, P., & Esmi, E. (2011). Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm. Information Sciences, 181(10), 1929–1950.
Vega, R., Guevara, E., Falcon, L., Sanchez, G., & Sossa, H. (2013). Blood vessel segmentation in retinal images using lattice neural networks. In Proceedings of the 12th Mexican International Conference on Artificial Intelligence (MICAI), LNAI (vol. 8265, pp. 529–540).
Vega, R., Sánchez, G., Falcón, L., Sossa, H., & Guevara, E. (2015). Retinal vessel extraction using lattice neural networks with dendritic processing. Computers in Biology and Medicine, 58, 20–30.
Zamora, E., & Sossa, H. (2016). Dendrite morphological neurons trained by stochastic gradient descent. In Proceedings of the 2016 IEEE Symposium Series on Computational Intelligence (SSCI 2016), Athens, Greece (pp. 1–8).
Zamora, E., & Sossa, H. (2017). Dendrite morphological neurons trained by stochastic gradient descent. Neurocomputing, 260, 420–431.
Acknowledgements
E. Zamora and H. Sossa would like to acknowledge UPIITA-IPN and CIC-IPN for the support to carry out this research. This work was economically supported by SIP-IPN (grant numbers 20160945, 20170836 and 20161116, 20170693, 20180730, 20180180), and CONACYT (grant number 155014 (Basic Research) and grant number 65 (Frontiers of Science). F. Arce acknowledges CONACYT for the scholarship granted toward pursuing his PhD studies.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this chapter
Cite this chapter
Sossa, H., Arce, F., Zamora, E., Guevara, E. (2018). Morphological Neural Networks with Dendritic Processing for Pattern Classification. In: Vergara Villegas, O., Nandayapa , M., Soto , I. (eds) Advanced Topics on Computer Vision, Control and Robotics in Mechatronics. Springer, Cham. https://doi.org/10.1007/978-3-319-77770-2_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-77770-2_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-77769-6
Online ISBN: 978-3-319-77770-2
eBook Packages: EngineeringEngineering (R0)