Abstract
We introduce a novel system of interconnected Self- Organizing Maps that can be used to build feedforward and recurrent networks of maps. Prime application of interconnected maps is in modelling systems that operate with multimodal data as for example in visual and auditory cortices and multimodal association areas in cortex. A detailed example of animal categorization in which the feedworward network of self-organizing maps is employed is presented. In the example we operate with 18-dimensional data projected up on the 19-dimensional hyper-sphere so that the “dot-product” learning law can be used. One potential benefit of the multimodal map is that it allows a rich structure of parallel unimodal processing with many maps involved, followed by convergence into multimodal maps. More complex stimuli can therefore be processed without a growing map size.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kohonen, T.: Self-Organising Maps, 3rd edn. Springer, Berlin (2001)
Gustafsson, L., Papliński, A.P.: Self-organization of an artificial neural network subjected to attention shift impairments and novelty avoidance: Implications for the development of autism. J. Autism and Dev. Disorder 34, 189–198 (2004)
Papliński, A.P., Gustafsson, L.: An attempt in modelling early intervention in autism using neural networks. In: Proc. Int. Joint Conf. Neural Networks, Budapest, Hungary, pp. 101–108 (2004)
Gustafsson, L., Papliński, A.P.: Neural network modelling of autism. In: Casanova, M.F. (ed.) Recent developments in autism research, pp. 100–134. Nova Science Publishers, Inc., Hauppauge (2005) (in press)
Papliński, A.P., Gustafsson, L.: Detailed learning in narrow fields - towards a neural network model of autism. In: Kaynak, O., Alpaydın, E., Oja, E., Xu, L. (eds.) ICANN 2003 and ICONIP 2003. LNCS, vol. 2714, pp. 830–838. Springer, Heidelberg (2003)
Gustafsson, L., Papliński, A.P.: Preoccupation with a restricted pattern of interest in modelling autistic learning. In: Palade, V., Howlett, R.J., Jain, L. (eds.) KES 2003. LNCS, vol. 2774, pp. 1122–1129. Springer, Heidelberg (2003)
Papliński, A.P., Gustafsson, L.: An attempt in modelling autism using self-organizing maps. In: Proc. 9th Intern. Conf. Neural Information Processing, Singapore, pp. 301–304 (2002)
Alahakoon, D., Halgamuge, S.K., Srinivasan, B.: Dynamic self-organizing maps with controlled growth for knowledge discovery. IEEE Trans. Neural Networks 11, 601–614 (2000)
Milano, M., Koumoutsakos, P., Schmidhuber, J.: Self-organizing nets for optimization. IEEE Trans. Neural Networks 15, 758–765 (2004)
Xu, P., Chang, C.H., Papliński, A.: Self-organizing topological tree for on-line vector quantization and data clustering. IEEE Tran. System, Man and Cybernetics, Part B: Cybernetics 35, 515–526 (2005)
Wallis, G., Rolls, E.: Invariant face and object recognition in the visual system. Progress in Neurobiology 51, 167–194 (1997)
Rolls, E., Milward, T.: A model of invariant object recognition in the visual system: learning rules, activation function, lateral inhibition, and information-based performance measures. Neural Computation 51, 2547–2572 (2000)
Mountcastle, V.B.: The columnar organization of the neocortex. Brain 120, 701–722 (1997)
Felleman, D.J., van Essen, D.C.: Distributed hierarchical processing in the primate cerebral cortex. Cerebral Cortex 1, 1–47 (1991)
Kandel, E.R., Schwartz, J.H., Jessel, T.M. (eds.): Principles of Neural Science, 4th edn. McGraw Hill, New York (2000)
Rolls, E.T.: Multisensory neuronal convergence of taste, somatosentory, visual, and auditory inputs. In: Calvert, G., Spencer, C., Stein, B.E. (eds.) The Handbook of multisensory processes, pp. 311–331. MIT Press, Cambridge (2004)
Huttenlocher, P.R., Dabholkar, A.S.: Regional differences in synaptogenesis in human cerebral cortex. J. Comparative Neurology 387, 161–178 (1997)
Rakic, P., Bourgeois, J.P., Goldman-Rakic, P.S.: Synaptic development of the cerebral cortex: implications for learning, memory, and mental illness. In: van Pelt, J., Comer, M.A., Uylings, H.B.M., Lopes da Silva, F.H. (eds.) Prog. Brain Research. Elsevier Sci., pp. 227–243 (1994)
Hopfield, J.: Neural networks and physical systems with emergent collective computational properties. Proc. Nat. Academy of Sci. USA 79, 2554–2588 (1982)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Papliński, A.P., Gustafsson, L. (2005). Multimodal FeedForward Self-organizing Maps. In: Hao, Y., et al. Computational Intelligence and Security. CIS 2005. Lecture Notes in Computer Science(), vol 3801. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11596448_11
Download citation
DOI: https://doi.org/10.1007/11596448_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-30818-8
Online ISBN: 978-3-540-31599-5
eBook Packages: Computer ScienceComputer Science (R0)