Abstract
This paper presents an unsupervised approach for learning of patterns with spatial and temporal information from a very small number of training samples. The method employs a spiking network with axonal conductance delays that learns the encoding of individual patterns as sets of polychronous neural groups, which emerge as a result of training. A similarity metric between sets, based on a modified version of the Jaccard index, is used for pattern classification. Two different neural connectivity models are evaluated on a data set consisting of hand-drawn digits that encode temporal information (i.e., from the starting to the end point of the digit). The results demonstrate that the approach can successfully generalize these patterns from a significantly small number of training samples.
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
Kelley, R., King, C., Tavakkoli, A., Nicolescu, M., Nicolescu, M., Bebis, G.: An architecture for understanding intent using a novel hidden markov formulation. International Journal of Humanoid Robotics 5(02), 203–224 (2008)
Schaal, S.: Is imitation learning the route to humanoid robots? Trends in Cognitive Sciences 3(6), 233–242 (1999)
Rekabdar, B., Shadgar, B., Osareh, A.: Learning teamwork behaviors approach: Learning by observation meets case-based planning. In: Ramsay, A., Agre, G. (eds.) AIMSA 2012. LNCS, vol. 7557, pp. 195–201. Springer, Heidelberg (2012)
Szatmáry, B., Izhikevich, E.M.: Spike-timing theory of working memory. PLoS Computational Biology 6(8), e1000879 (2010)
Paugam-Moisy, H., Martinez, R., Bengio, S.: Delay learning and polychronization for reservoir computing. Neurocomputing 71(7), 1143–1158 (2008)
Karimpouli, S., Fathianpour, N., Roohi, J.: A new approach to improve neural networks’ algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network. Journal of Petroleum Science and Engineering 73(3), 227–232 (2010)
Charniak, E., Goldman, R.P.: A Bayesian model of plan recognition. Artificial Intelligence 64(1), 53–79 (1993)
Tao, X., Michel, H.E.: Data Clustering Via Spiking Neural Networks through Spike Timing-Dependent Plasticity. In: IC-AI, pp. 168–173 (2004)
Izhikevich, E.M.: Polychronization: computation with spikes. Neural Computation 18(2), 245–282 (2006)
Jaccard, P.: The distribution of the flora in the alpine zone. 1. New Phytologist 11(2), 37–50 (1912)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Rekabdar, B., Nicolescu, M., Kelley, R., Nicolescu, M. (2014). Unsupervised Learning of Spatio-temporal Patterns Using Spike Timing Dependent Plasticity. In: Goertzel, B., Orseau, L., Snaider, J. (eds) Artificial General Intelligence. AGI 2014. Lecture Notes in Computer Science(), vol 8598. Springer, Cham. https://doi.org/10.1007/978-3-319-09274-4_28
Download citation
DOI: https://doi.org/10.1007/978-3-319-09274-4_28
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-09273-7
Online ISBN: 978-3-319-09274-4
eBook Packages: Computer ScienceComputer Science (R0)