Abstract
In our previous study, task segmentation by mnSOM implicitly assumes that winner modules corresponding to subsequences in the same class share the same label. This paper proposes to do task segmentation by applying various clustering methods to the resulting mnSOM without using the above assumption. Firstly we use the conventional hierarchical clustering. It assumes that the distances between any pair of modules are provided with precision, but this is not exactly true. Accordingly, this is followed by a clustering based on only the distance between spatially adjacent modules with modification by their temporal contiguity. This clustering with spatio-temporal contiguity provides superior performance to the conventional hierarchical clustering and comparable performance with mnSOM using the implicit assumption.
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
Duda, R.O., Hart, P.E., Stork, D.G.: Pattern Classification. Wiley-Interscience, Chichester (2001)
Furukawa, T., Tokunaga, K., Kaneko, S., Kimotsuki, K., Yasui, S.: Generalized self-organizing maps (mnSOM) for dealing with dynamical systems. In: Proc. of NOLTA 2004, Fukuoka, Japan, pp. 231–234 (2004)
Jacobs, R., Jordan, M., Nowlan, S., Hinton, G.: Adaptive Mixtures of Local Experts. Neural Computation 3, 79–87 (1991)
Tani, J., Nolfi, S.: Learning to perceive the world as articulated: an approach for hierarchical learning in sensory-motor systems. Neural Networks 12, 1131–1141 (1999)
Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (1995)
Williams, R.J., Zipser, D.: Gradient-based learning algorithms for recurrent networks and their computational complexity. In: Chauvin, Y., Rumelhart, D. (eds.) Backpropagation: Theory, Architectures and Applications, pp. 433–486. Lawrence Erlbaum, Mahwah (1992)
Wolpert, D.M., Kawato, M.: Multiple paired forward and inverse models for motor control. Neural Networks 11, 1317–1329 (1998)
Aziz Muslim, M., Ishikawa, M., Furukawa, T.: A New Approach to Task Segmentation in Mobile Robots by mnSOM. In: Proc. of 2006 IEEE WCCI (IJCNN2006 Section), Vancouver, Canada, pp. 6542–6549 (2006)
Aziz Muslim, M., Ishikawa, M., Furukawa, T.: Task Segmentation in a Mobile Robot by mnSOM: A New Approach To Training Expert Modules. Neural Computing and Application, Springer (to appear, 2007)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Muslim, M.A., Ishikawa, M., Furukawa, T. (2008). Task Segmentation in a Mobile Robot by mnSOM and Clustering with Spatio-temporal Contiguity. In: Ishikawa, M., Doya, K., Miyamoto, H., Yamakawa, T. (eds) Neural Information Processing. ICONIP 2007. Lecture Notes in Computer Science, vol 4985. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-69162-4_112
Download citation
DOI: https://doi.org/10.1007/978-3-540-69162-4_112
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-69159-4
Online ISBN: 978-3-540-69162-4
eBook Packages: Computer ScienceComputer Science (R0)