Abstract
Competitive learning algorithms are statistically driven schemes requiring that the training samples are both representative and randomly ordered. Within the frame of self-organization, the latter condition appears as a paradoxical unrealistic assumption about the temporal structure of the environment. In this paper, the resulting vulnerability to continuously changing inputs is illustrated in the case of a simple space discretization task. A biologically motivated local anti-Hebbian modulation of the Hebbian weights is introduced, and successfully used to stabilize this network under real-time-like conditions.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
Carpenter, G.A., Grossberg, S.: ART 2: self-organization of stable category recognition codes for analog input patterns. Applied Optics, 26 (1987) 4919–4930
Földiák, P.: Forming sparse representations by local anti-Hebbian learning. Biol. Cyber., 64:2 (1990) 165–170
Kohonen, T.: Self Organization and Associative Memory. Springer Verlag, Berlin (1984)
Miller, E.K., Li, L., Desimone, R.: Activity of neurons in anterior inferior temporal cortex during a short-term memory task. J. of Neuroscience 13:4 (1993) 1460–1478
Mille, E.K., Desimone, D.: Parallel neuronal mechanisms for short-term memory Science 263 (1994) 520–522
Zucker, R.S.: Short-term synaptic plasticity. Ann. Rev. Neurosci. 12 (1989) 13–31
Vogels, R., Orban, G.A.: Activity of inferior temporal neurons during orientation discrimination with successively presented gratings. J. of Neurophysiology 71:4 (1994) 1428–1451
McClelland, J.L., McNaughton, B.L., O'Reilly, R.C.: Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological Review 102:3 (1995) 419–457
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Tavitian, S., Fomin, T., Lőrincz, A. (1996). Stabilizing competitive learning during on-line training with an anti-Hebbian weight modulation. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_118
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_118
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive