Abstract
This paper presents an overview of the current status of lattice based dendritic computing. Roughly speaking, lattice based dendritic computing refers to a biomimetic approach to artificial neural networks whose computational aspects are based on lattice group operations. We begin our presentation by discussing some important processes of biological neurons followed by a biomimetic model which implements these processes. We discuss the reasons and rationale behind this approach and illustrate the methodology with some examples. Global activities in this field as well as some potential research issues are also part of this discussion.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
McCulloch, W., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics 5, 115–133 (1943)
Rosenblatt, F.: The perceptron: A probabilistic model for information storage and organization in the brain. Psychological Review 65, 386–408 (1958)
Minsky, M.L., Papert, S.A.: Perceptrons. MIT Press, Cambridge (1969)
Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Academy of Sciences USA 79, 2554–2558 (1982)
Hopfield, J.J.: Neurons with graded response have collective computational properties like those of two state neurons. Proc. Nat. Academy of Sciences USA 81, 3088–3092 (1984)
Hopfield, J.J., Tank, D.W.: Computing with neural circuits. Science 233, 625–633 (1986)
Ritter, G.X., Urcid, G.: Lattice algebra approach to single neuron computation. IEEE Trans. on Neural Networks 14(2), 282–295 (2003)
Lee, W.C.A., et al.: Dynamic remodeling of dendritic arbors in GABAergic interneurons of adult visual cortex. PLoS Biology 4(2), 271–280 (2006)
The Third Source: A message of hope for education. The Neuron, in Media Gallery (2010), http://www.thethirdsource.org/media/charts-and-graphs
Dayan, P., Abott, L.F.: Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. MIT Press, Boston (2006)
Eccles, J.C.: The Understanding of the Brain. McGraw-Hill, New York (1977)
Sejnowski, T.J., Qian, N.: Synaptic integration by electro-diffusion in dendritic spines. In: McKenna, T., Davis, J., Zornetzer, S.F. (eds.) Single Neuron Computation. Academic Press, New York (1992)
Rall, W., Segev, I.: Functional Possibilities for Synapses on Dendrites and Dendritic Spines. In: Edelman, G.M., Gall, E.E., Cowan, W.M. (eds.) Synaptic Function, pp. 605–636. John Wiley & Sons, New York (1987)
Koch, C., Segev, I. (eds.): Methods in Neuronal Modeling: From Synapses to Networks. MIT Press, Cambridge (1989)
Segev, I.: Dendritic Processing. In: Arbib, M.A. (ed.) The Handbook of Brain Theory and Neural Networks, pp. 282–289. MIT Press, Boston (1998)
Mel, B.W.: Why have Dendrites? A Computational Perspective. In: Dendrites, S.G., Spruston, N., Hausser, M.D. (eds.), pp. 271–289. Oxford University Press (1999)
Wei, D.S., et al.: Compartmentalized and binary behavior of terminal dendrites in hippocampal pyramidal neurons. Science 293, 2272–2275 (2001)
Won, Y., Gader, P.D., Coffield, P.: Morphological shared-weight networks with applications to automatic target recognition. IEEE Trans. Neural Networks 8(5), 1195–1203 (1997)
Mel, B.W.: Synaptic integration in excitable dendritic trees. Journal of Neurophysiology 70, 1086–1101 (1993)
Holmes, W.R., Rall, W.: Electronic Models of Neuron Dendrites and Single Neuron Computation. In: McKenna, T., Davis, J., Zornetzer, S.F. (eds.) Single Neuron Computation, pp. 7–25. Academic Press, New York (1992)
Shepherd, G.M.: Canonical Neurons and their Computational Organization. In: McKenna, T., Davis, J., Zornetzer, S.F. (eds.) Single Neuron Computation, pp. 27–55. Academic Press, San Diego (1992)
McKenna, T., Davis, J., Zornetzer, S.E. (eds.): Single Neuron Computation. Academic Press, San Diego (1992)
Arbib, M.A. (ed.): The Handbook of Brain Theory and Neural Networks. MIT Press, Boston (1998)
Koch, C., Poggio, T.: Multiplying with Synapses. In: McKenna, T., Davis, J., Zornetzer, S.F. (eds.) Single Neuron Computation, pp. 315–345. Academic Press, New York (1992)
Koch, C.: Biophysics of Computation: Information Processing in Single Neurons. Oxford University Press (1999)
Yu, A.J., Giese, M.A., Poggio, T.A.: Biophysiologically plausible implementations of the maximum operation. Neural Computation 14(12), 2857–2881 (2002)
Lampl, I., Ferster, D., Poggio, T., Riesenhuber, M.: Intracellular measurements of spatial integration and the Max operation in complex cells of the cat primary visual cortex. Journal of Neurophysiology 92, 2704–2713 (2004)
Ritter, G.X., Urcid, G., Selfridge, R.: Minimax dendrite computation. In: Proc. ANNIE, ASME, St. Louis, Missouri, vol. 12, pp. 75–80 (2002)
Ritter, G.X., Iancu, L., Urcid, G.: Morphological perceptrons with dendritic structure. In: Proc. FUZZ-IEEE, St. Louis, Missouri, pp. 1296–1301 (2003)
Ritter, G.X., Iancu, L.: Lattice algebra approach to neural networks and pattern classification. In: IAPR Proc. 6th Open German-Russian Workshop on Pattern Recognition and Image Understanding, Katun Village, Altai Region, Russian Fed., pp. 18–21 (2003)
Ritter, G.X., Iancu, L., Urcid, G.: Neurons, dendrites, and pattern classification. In: Sanfeliu, A., Ruiz-Shulcloper, J. (eds.) CIARP 2003. LNCS, vol. 2905, pp. 1–16. Springer, Heidelberg (2003)
Ritter, G.X., Iancu, L.: A morphological auto-associative memory based on dendritic computing. In: Proc. IEEE, IJCNN, vol. 2, pp. 915–920 (2004)
Urcid, G., Ritter, G.X., Iancu, L.: Single layer morphological perceptron solution to the N-bit parity problem. In: Sanfeliu, A., MartÃnez Trinidad, J.F., Carrasco Ochoa, J.A. (eds.) CIARP 2004. LNCS, vol. 3287, pp. 171–178. Springer, Heidelberg (2004)
Urcid, G.: Transformations of neural inputs in lattice dendrite computation. In: Proc. SPIE: Math. Methods in Pattern and Image Analysis, San Diego, CA, vol. 5916, pp. 201–212 (2005)
Ritter, G.X., Urcid, G., Schmalz, M.S.: Lattice associative memories that are robust in the presence of noise. In: Proc. SPIE: Math. Methods in Pattern and Image Analysis, San Diego, CA, vol. 5916, pp. 255–260 (2005)
Myers, D.S.: The synaptic morphological perceptron. In: Proc. SPIE: Math. of Data/Image Pattern Recognition, Compr. and Encryp., San Diego, CA, vol. 6315, pp. 63150B:1–63150B:11 (2006)
Davidson, J.L., Ritter, G.X.: A theory of morphological neural networks. In: Proc. SPIE: Digital Optical Computing II, San Diego, CA, vol. 1215, pp. 378–388 (1990)
Davidson, J.L.: Simulated annealing and morphological neural networks. In: Proc. SPIE: Image Algebra and Morphological Image Proc. III, San Diego, CA, vol. 1769, pp. 119–127 (1992)
Davidson, J.L., Hummer, F.: Morphology neural networks: An introduction with applications. IEEE Systems and Signal Processing 12(2), 177–210 (1993)
Ritter, G.X., Sussner, P.: An introduction to morphological neural networks. In: Proc. 13th Int. Conf. on Pattern Recognition, Vienna, Austria, pp. 709–717 (1996)
Ritter, G.X., Sussner, P.: Associative memories based on lattice algebra. In: IEEE Int. Conf. Systems, Man, and Cybernetics, Orlando, FL, pp. 3570–3575 (1997)
Ritter, G.X., Sussner, P., Diaz de Leon, J.L.: Morphological associative memories. IEEE Trans. Neural Networks 9(2), 281–293 (1998)
Petridis, V., Kaburlasos, V.G.: Fuzzy lattice neural network (FLNN): A hybrid model for learning. IEEE Trans. Neural Networks 9(5), 877–890 (1998)
Ritter, G.X., Diaz de Leon, J.L., Sussner, P.: Morphological bidirectional associative memories. Neural Networks 12, 851–867 (1999)
Gabrys, B., Bargiela, A.: General fuzzy min-max neural network for clustering and classification. IEEE Trans. on Neural Networks 11(3), 769–783 (2000)
Sussner, P., Valle, M.E.: Gray-scale morphological associative memories. IEEE Trans. on Neural Networks 17(3), 559–570 (2006)
Kaburlasos, V.G.: Towards a Unified Modeling and Knowledge Representation Based on Lattice Theory, Computational Intelligence. SCI, vol. 27. Springer, Heidelberg (2006)
Kaburlasos, V.G., Ritter, G.X. (eds.): Computational Intelligence Based on Lattice Theory. SCI, vol. 67. Springer, Heidelberg (2007)
Sossa-A., J.H., Barron-F., R.: Extended α − β associative memories. Revista Mexicana de FÃsica 53(1), 10–20 (2007)
Sussner, P., Laureano, E.E.: Morphological perceptrons with competitive learning: Lattice-theoretical framework and constructive learning algorithm. Information Sciences 181(10), 1929–1950 (2011)
Urcid, G., Ritter, G.X.: C-means clustering of lattice auto-associative memories for endmember approximation. In: Adv. in Knowledge-Based and Intelligent Inf. and Eng. Systems, San Sebastian, Spain, pp. 2140–2149. IOS Press (2012)
Valle, M.E., Sussner, P.: Quantale-based autoassociative memories with an application to the storage of color images. Pattern Recognition Letters 34(14), 1589–1601 (2013)
Iancu, L.: Lattice Algebra Approach to Neural Computation. Ph.D. Thesis, University of Florida, Gainesville, FL (2005)
Ritter, G.X., Gader, P.: Fixed Points of Lattice Transforms and Lattice Associative Memories. In: Hawkes, P. (ed.) Advances in Imaging and Electron Physics, vol. 144, pp. 165–242. Elsevier, San Diego (2006)
Ritter, G.X., Schmalz, M.S.: Learning in lattice neural networks that employ dendritic computing. In: Proc. IEEE Inter. Conf. on Fuzzy Systems, Vancouver, BC, Canada, pp. 209–215 (2006)
Ritter, G.X., Urcid, G.: Learning in lattice neural networks that employ dendritic computing. In: Kaburlasos, V.G., Ritter, G.X. (eds.) Computational Intelligence based on Lattice Theory. SCI, vol. 67, pp. 25–44. Springer, Heidelberg (2007)
Ritter, G.X., Urcid, G.: Lattice neural networks with spike trains. In: Corchado, E., Graña Romay, M., Manhaes Savio, A. (eds.) HAIS 2010, Part II. LNCS, vol. 6077, pp. 367–374. Springer, Heidelberg (2010)
Chyzhyk, D., Graña, M.: Optimal hyperbox shrinking in dendritic computing applied to Alzheimer’s disease detection in MRI. In: Corchado, E., Snášel, V., Sedano, J., Hassanien, A.E., Calvo, J.L., Ślęzak, D. (eds.) SOCO 2011. AISC, vol. 87, pp. 543–550. Springer, Heidelberg (2011)
Ritter, G.X., Urcid, G.: Perfect recall from noisy input patterns with a dendritic lattice associative. In: Proc. IEEE, IJCNN, San Jose, CA, pp. 503–510 (2011)
Urcid, G., Ritter, G.X., Valdiviezo-N., J.C.: Grayscale image recall from imperfect inputs with a two layer dendritic lattice associative memory. In: Proc. IEEE, 3rd Congr. on Nature and Biologically Inspired Computing, Salamanca, Spain, pp. 268–273 (2011)
Chyzhyk, D.: Bootstrapped dendritic classifiers for Alzheimer’s disease classification on MRI features. In: Adv. in Knowledge-Based and Intelligent Inf. and Eng. Systems, pp. 2251–2258. IOS Press (2012)
Chyzhyk, D., Graña, M., Savio, A., Maiora, J.: Hybrid dendritic computing with kernel-LICA applied to Alzheimer’s disease detection in MRI. Neurocomputing 75, 72–77 (2012)
Ritter, G.X., Chyzhyk, D., Urcid, G., Graña, M.: A novel lattice associative memory based on dendritic computing. In: Corchado, E., Snášel, V., Abraham, A., Woźniak, M., Graña, M., Cho, S.-B. (eds.) HAIS 2012, Part II. LNCS, vol. 7209, pp. 491–502. Springer, Heidelberg (2012)
Abrahamsson, T., Cathala, L., Matsui, K., Shigemoto, R., DiGregorio, D.A.: Thin dendrites of cerebellar interneurons confer sublinear synaptic integration and a gradient of short-term plasticity. Neuron 73, 1159–1172 (2012)
Caze, R.D., Humphries, M., Gutkin, B.: Passive dendrites enable single neurons to compute linearly non-separable functions. PLoS Computational Biology 9(2) (2013)
Urcid, G., Ritter, G.X., Valdiviezo-N., J.C.: Dendritic lattice associative memories for pattern classification. In: Proc. IEEE, 4th Congr. on Nature and Biologically Inspired Computing, Mexico DF, pp. 181–187 (2012)
Graña, M., Gonzalez-A., A.I.: Learning parsimonious dendritic classifiers. Neurocomputing 109, 3–8 (2013)
Sossa, H., Guevara, E.: Efficient training for dendrite morphological neural networks. Neurocomputing 131, 132–142 (2014)
Ritter, G.X., Urcid, G., Valdiviezo-N, J.C.: Two lattice metrics dendritic computing for pattern recognition. Accepted for publication in FUZZ-IEEE (2014)
Ritter, G.X., Iancu, L.: A lattice algebra approach to neural computation. In: Handbook of Computational Geometry for Pattern Recognition, Computer Vision, Neurocomputing and Robotics, pp. 97–129. Springer, Heidelberg (2005)
Vega, R., Guevara, E., Falcon, L.E., Sánchez-Ante, G., Sossa, H.: Blood vessel segmentation in retinal images using lattice neural networks. In: Castro, F., Gelbukh, A., González, M. (eds.) MICAI 2013, Part I. LNCS, vol. 8265, pp. 532–544. Springer, Heidelberg (2013)
Caro-C, D.E.: Méndez-V A.: Computing the concept lattice using dendritical neural networks. In: Proc. 10th Int. Conf. on Concept Lattices and Their Applications, pp. 141–152 (2013)
Wille, R.: Formal concept analysis as mathematical theory of concepts and concept hierarchies. In: Ganter, B., Stumme, G., Wille, R., et al. (eds.) Formal Concept Analysis. LNCS (LNAI), vol. 3626, pp. 1–33. Springer, Heidelberg (2005)
Stumme, G., Taouil, R., Bastide, Y., Pasquir, N., Lakhal, L.: Fast computation of concept lattices using data mining techniques. In: Proc. 7th Int. Workshop on Knowledge Representation and Databases, pp. 129–139 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ritter, G.X., Urcid, G. (2014). Lattice Based Dendritic Computing: A Biomimetic Approach to ANNs. In: Bayro-Corrochano, E., Hancock, E. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2014. Lecture Notes in Computer Science, vol 8827. Springer, Cham. https://doi.org/10.1007/978-3-319-12568-8_89
Download citation
DOI: https://doi.org/10.1007/978-3-319-12568-8_89
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-12567-1
Online ISBN: 978-3-319-12568-8
eBook Packages: Computer ScienceComputer Science (R0)