Abstract
The learning of temporal sequences is an extremely important component of human and animal behaviour. As well as the motor control involved in routine behaviour such as walking, running, talking, tool use and so on, humans have an apparently remarkable capacity for learning (and subsequently reproducing) temporal sequences. A new connectionist model of temporal sequence learning is described which is based on recurrent self-organising maps. The model is shown to be both powerful and robust, and to exhibit a strong generalisation effect not found in simple recurrent networks (SRN). The model combines two important developments in artificial neural networks; recursion and self-organising maps (SOM). Both are found in the primate cortex; topological maps appear to be ubiquitous in the cerebral cortex of higher animals, especially in the primary sensory areas, and the neuroanatomy of the cortex also reveals numerous and consistent recurrent linkages between regions.
Preview
Unable to display preview. Download preview PDF.
References
Garry J. Briscoe. Adaptive Behavioural Cognition. PhD thesis, School of Computing, Curtin University of Technology, Perth, Western Australia, 1997.
Axel Cleeremans. Mechanisms of Implicit Learning: Connectionist Models of Sequence Processing. The MIT Press, A Bradford Book; Cambridge, MA, 1993.
Jeffrey L. Elman. Finding Structure in Time. Cognitive Science, 14:179–211, 1990.
Jeffrey L. Elman. Learning and development in neural networks: the importance of starting small. Cognition, 48:71–99, 1993.
Michael I. Jordan. Attractor Dynamics and Parallelism in a Connectionist Sequential Machine. In Proceedings of the Eighth Annual Conference of the Cognitive Science Society, pages 112–127, 1986.
Michael I. Jordan. Serial order: A parallel, distributed processing approach. In J.L. Elman and D.E. Rumelhart, editors, Advances in Connectionist Theory: Speech. Hillsdale, NJ: Erlbaum, 1989.
Michael I. Jordan and David A. Rosenbaum. Action. In Michael I. Posner, editor, Foundations of Cognitive Science, chapter 18, pages 727–767. The MIT Press: A Bradford Book: Cambridge, MA, 1989.
Jari Kangas. Time-Delayed Self-Organizing Maps. Proc. IJCNN'Sg Int. Joint Conf. on Neural Networks, 11:331–336, 1989.
K.J. Lang, A.H. Waibel, and G.E. Hinton. A Time-Delay Neural Network Architecture for Isolated Word Recognition. Neural Networks, 3:33–43, 1990. Reproduced in Readings in Machine Learning Shavlik and Dietterich (eds), Morgan Kaufmann, 1990, pages 150–170.
J.C. Scholtes. Recurrent Kohonen Self-Organization in Natural Language Processing. In T. Kohonen, K. Mäkisara, O. Simula, and J. Kangas, editors, Artificial Neural Networks — Volume 2 (Proceedings of the 1991 International Conference on Artificial Neural Networks (ICANN-91), Espoo, Finland, (June 1991), pages 1751–1754. North-Holland, 1991.
Noel E. Sharkey and Amanda J.C. Sharkey. Separating Learning and Representation. In Stefan Wermter, Ellen Riloff, and Gabriele Scheler, editors, Connectionist, Statistical and Symbolic Approaches to Learning for Natural Language Processing, pages 17–32. Springer, 1996.
Harel Z. Shouval and Michael P. Perrone. Post-hebbian learning rules. In Michael A. Arbib, editor, The Handbook of Brain Theory and Neural Networks, pages 745–748. The MIT Press: A Bradford Book: Cambridge, MA, 1995.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Briscoe, G., Caelli, T. (1997). Learning temporal sequences in recurrent self-organising neural nets. In: Sattar, A. (eds) Advanced Topics in Artificial Intelligence. AI 1997. Lecture Notes in Computer Science, vol 1342. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-63797-4_96
Download citation
DOI: https://doi.org/10.1007/3-540-63797-4_96
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63797-4
Online ISBN: 978-3-540-69649-0
eBook Packages: Springer Book Archive