Abstract
The study addresses the cyclically temporal aspect of sequence recognition, storage and recall using the Recurrent Oscillatory Self-Organizing Map (ROSOM), first introduced by Kaipainen, Papadopoulos and Karhu (1997). The unique solution of the network is that oscillatory States are assigned to network units, corresponding to their `readiness-to-fire'. The ROSOM is a categorizer, a temporal sequence storage system and a periodicity detector designed for use in an ambiguous cyclically repetitive environment. As its external input, the model accepts a multidimensional stream of environment-describing feature configurations with implicit periodicities. The output of the model is one or a few closed cycles abstracted from such a stream, mapped as trajectories on a two-dimensional sheet with an organization reminiscent of multi-dimensional scaling. The model's capabilities are explored with a variety of workbench data.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ans, B. (1990), 'Neuromimetic model for storage and recall of temporal sequences'. Comptes Rendus de l'Académie des Sciences, Serie III, 311, 127-132.
Ans, B., Coiton, Y., Gilhodes, J-C. and Velay, J-L. (1994), 'A Neural Network Model for Temporal Sequence Learning and Motor Programming', Neural Networks 7(9), pp. 1461-1476.
Carpenter, G.A. and Grossberg, S. (1987), 'ART 2: Self-organization of stable category recognition codes for analog input patterns', Applied Optics 26, 4919-4930.
Chappell, G.J. and Taylor, J.G. (1993), 'The temporal Kohonen map'. Neural Networks 6(3), pp. 441-445.
Cunningham, R.K. and Waxman, A.M. (1994), 'Diffusion-enhancement bilayer: realizing long-range apparent motion and spatiotemporal grouping in a neural architecture', Neural Networks, 7(6/7), pp. 895-892.
Elman, J. (1990), 'Finding structure in time', Cognitive Science 14, pp. 179-211.
Euliano, N.R. and Principe, J.C. (1997), 'Spatio-temporal self-organizing feature maps', Computational Neuro-Engineering Laboratory, Department of Electrical Engineering, University of Florida. http://knicks.ee.ufl.edu/~neil/tempkohltemporal.html.
Grossberg, S. (1976), 'Adaptive pattern classification and universal recoding. 1. Parallel development and coding of neural feature detectors', Biological Cybernetics 23, pp. 121-134.
Haken, H., Kelso, J.A.S. and Bunz, H. (1985), 'A theoretical model of phase transitions in human hand movements', Biological Cybernetics 51, 347-356.
Hanson, C. and Hanson, S.T. (1996), 'Development of schemata during event parsing: Neisser's perceptual cycle as a recurrent connectionist network', Journal of Cognitive Neuroscience 8(2), pp. 119-134.
Hoekstra, A. and Drossaers, M. F. (1993), 'An extended Kohonen feature map for sentence recognition', Gielen, S. and Kappen, B. (eds.). Proceedings of the ICANN '93. http://www.ph.tn.tudelft.nl/Research/neural/generalizatio/papers/icann/93/icann93.html
James, D. and Miikkulainen, R. (1995), 'SARDNET: A self-organizing feature map for sequences', Tesauro, G., Touretzky, D. and Leen, T. (eds.). Advances in Neural Information Processing Systems 7. Cambridge, MA: MIT Press.
Jones, M.R. (1976), 'Time, our lost dimension: Toward a new theory of perception, attention and memory', Psychological Review 83, pp. 323-355.
Jones, M.R. (1981), 'Only time can tell: On the topology of mental space and time', Critical Inquiry Vol. 7, Number 3.
Jordan, M.I. (1986), 'Serial order: A parallel processing approach', San Diego: University of California, Center for Human Information Processing. ICS Report 8604.
Kaipainen, M. (1996), 'Representing and remotivating musical processes: Modeling a recurrent musical ecology', Swets and Zeitlinger. Journal of New Music Research 25(2).
Kaipainen, M., Papadopoulos, P. and Karhu, P. (1997), 'Recurrent oscillatory self-organizing map: Learning and entrainment to multiple periodicities', Proceedings of the Midwest Artificial Intelligence and Cognitive Science Conference, Dayton, Ohio, June 1997.
Kaipainen, M., Toiviainen, P. and Louhivuori, J. (1995a), 'A self-organizing map that recognizes and generates melodies', Pylkkiinen, P. and Pylkkö, P. (eds.). New Directions in Cognitive Science. (Proceedings of the International Symposium, Saariselka, 4-9 August 1995). Helsinki: Finnish Artificial Intelligence Society.
Kaipainen, M., Toiviainen, P. and Louhivuori, J. (1995b), 'A self-organizing map that generates melodies: modeling and testing spontaneously developing implicit Grammars', Proceedings of the International Congress in Music and AI, Edinburgh, 1995.
Kangas, J. (1990), Representation of Time-Dependent Signals in Self-Organizing Maps. Unpublished licenciate's thesis: Helsinki University of Technology, Dept. of Computer Science.
Kangas, J. (1991), 'Time-dependent self-organizing maps for speech recognition', Kohonen, T., Makisara, K., Simula, O. and Kangas, J. (1991), Artificial Neural Networks. Proceedings of the ICANN-91, Espoo, Finland. North-Holland: Elsevier Science Publishers.
Kargupta, H. and Ray, S.R. (1994), 'Temporal sequence processing based on the biological reaction-diffusion process', IEEE Proceedings of the International Conference on Neural Networks, Vol. 4, pp. 2315-2320.
Kohonen, T. (1982), 'Self-organized formation of topologically correct feature maps', Biological Cybernetics 43, pp. 59-69.
Kohonen, T. (1984), SeIf-Organisation and Associative Memory, Berlin: Springer-Verlag.
Kohonen, T. (1990), 'The Self-Organizing Map', Proceedings of the IEEE, Vol. 78, No. 9, Sept. 1990.
Kohonen, T. (1991), 'The hypermap architecture', Kohonen, T., Mäkisara, K., Simula, O. and Kangas, J. (eds.), Artificial Neural Networks. Proceedings of the ICANN-91, Espoo, Finland. North-Holland: Elsevier Science Publishers.
Kohonen, T. (1995), Self-organizing Maps. Berlin: Springer-Verlag.
Large, E. and Kolen, J. F. (1994), 'Resonance and perception of musical meter', Connection Science, Vol. 6, Numbers 2 & 3.
McAuley, J.D. (1994), 'Finding Metrical Structure in time', Mozer, M.C., Smolensky, P., Touretzky, D.S., Elman, J.L. and Weigend, A.S. (eds.), (1993). Proceedings of the 1993 Connectionist Models Summer School.
McAuley, J.D. (1995), Perception of Time as Phase: Toward an Adaptive-Oscillator Model of Rhythmic Pattern Processing. Ph.D. thesis, Indiana University, Bloomington, IN. Cognitive Science Program, Research Report 151, 1995.
McClelland, J. L., Rumelhart, D.E. and the PDP Research Group (1986), Parallel Distributed Processing: Explorations in the microstructure of cognition. 2. Psychological and biological models, Cambridge: MIT Press.
Minsky, M. (1986), The Society of Mind. New York: Simon & Schuster.
Morasso, P. (1991), 'Self-organizing feature-maps for cursive script recognition', Kohonen, T., Miikisara, K., Simula, O. and Kangas, J. (1991), Artificial Neural Networks. Proceedings of the ICANN-91, Espoo, Finland. North-Holland: Elsevier Science Publishers.
Neisser, U. (1976), Cognition and Reality. Principles and Implications of Cognitive Psychology. San Fransisco: W.H. Freeman and Company.
Port, R. and Anderson, S. (1989). 'Recognition of melody fragments in continuously performed music', Olson, G. and Smith, E. (eds.) Proceedings of the Eleventh Annual Meeting of the Cognitive Science Society. Hillsdale: Erlbaum.
Port, R.F., Cummins, F. and McAuley, J.D. (1995), 'Naive time, temporal patterns, and human audition', Port, R. and Gelder, T. van (eds.), Mind as Motion. Explorations in the Dynamics of Cognition. Cambridge, MA: MIT Press.
Reiss, M. and Taylor, J.G. (1991), 'Storing temporal sequences', Neural Networks, 5(6), 961-970.
Ritter, H. and Kohonen, T. (1989), 'Self-organizing semantic maps', Berlin: Springer. Biological Cybernetics 61, pp. 241-254.
Rosen, R. (1970), Dynamical System Theory in Biology Stability. Theory and Its Applications. Vol. 1. New York: Wiley.
Ruwisch, D., Bode, M. and Purwins, H. G. (1993), 'Parallel hardware implementation of Kohonen's algorithm with an active', Neural Networks 6(8), pp. 1147-1157.
Schöner, G., Haken, H. and Kelso, J.A.S. (1986), 'A stochastic theory of phase transitions in human hand movement', Biological Cybernetics 53, 442-452.
Shimohara, K., Uchiyama, T., and Tokunaga, Y. (1994). 'Subconnection neural network for event driven temporal sequence processing', Neural Networks 6(5), pp 709-718.
Smolensky, P. (1988), 'On the proper treatment of connectionism', Behavioral and Brain Sciences; 11(1), pp. 1-74.
Suga, N. (1988), 'What does single-unit analysis in the auditory cortex tell us about information processing in the auditory system?', Rakic, P. and Singer, W. (eds.), Neurobiology of Neocortex. John Wiley & Sons Limited.
Torras, C. (1985), Temporal-Pattern Learning in Neural Models, Berlin: Springer Verlag.
Wall, J.T. (1988), 'Variable organization in cortical maps of the skin as an indication of the lifelong adaptive capabilities of circuits in the mammalian brain', TINS, Vol. 11, No. 12.
Zandhuis, J.A. (1992), 'Storing sequential data in self-organizing feature maps', Nijmegen, The Netherlands: Max-Planck-Insitute ftir Psycholinguistik. Internal Report MPI-NL-TG-4/92.
Rights and permissions
About this article
Cite this article
Kaipainen, M., Karhu, P. Bringing Knowing-When and Knowing-What Together: Periodically Tuned Categorization and Category-Based Timing Modeled with the Recurrent Oscillatory Self-Organizing Map (ROSOM). Minds and Machines 10, 203–229 (2000). https://doi.org/10.1023/A:1008317204895
Issue Date:
DOI: https://doi.org/10.1023/A:1008317204895