Abstract
Computational tasks related to processing and recognition of natural signal require identification of complex patterns and relationships in massive quantities of low precision, ambiguous noisy data. While state-of-the-art techniques and architectures fail to provide sufficient solutions, cortical neural networks have an inherent computational power in this domain. A recently-introduced Liquid-State-Machine (LSM) paradigm provides a computational framework for applying a model of cortical neural microcircuit as a core computational unit in classification and recognition tasks of real-time temporal data. In this study we apply the concept of “Neural Cliques” and extend the computational power of the LSM framework by closing the loop. By incorporating functions of readout, reward and feedback, we implement such a closed-loop framework of neural architecture in classification and recognition tasks of real-time temporal data. This approach is inspired by several neurobiological findings from ex-vivo multi-cellular electrical recordings and injection of dopamine to the neural culture. Finally, we illustrate the performance of the proposed architecture in word-recognition tasks.
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
W. Maass, T. Natschläger, and H. Markram. Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation, 14(11):2531–2560 (2002).
W. Maass, T. Natschläger, and H. Markram. Computational models for generic cortical microcircuits. In J. Feng, editor, Computational Neuroscience: A Comprehensive Approach, chapter 18, pages 575–605. Chapman & Hall/CRC, Boca Raton, (2004)
Schultz W.: Neural coding of basic reward terms of animal learning theory, game theory, microeconomics and behavioural ecology. Curr Opin Neurobiol. Apr; 14(2):139–47 (2004)
D. Eytan, A. Minerbi, N. Ziv and S. Marom. Dopamine-induced Dispersion of Correlations Between Action Potentials in Networks of Cortical Neurons. J. Neurophysiol. 92:1817–1824 (2004)
G. Silberberg, A. Gupta and H. Markram: Stereotypy in neocortical microcircuits, Trends Neurosci. May;25(5):227–30 (2002)
M Tsodyks, K. Pawelzik, H. Markram, Neural networks with dynamic synapses. Neural Computation 10, 821–835 (1998)
T. Natschlager, H. Markram, and W. Maass. Computer models and analysis tools for neural microcircuits. In R. Kötter, editor, A Practical Guide to Neuroscience Databases and Associated Tools, chapter 9. Kluver Academic Publishers (Boston), 2002. in press. (http://www.lsm.tugraz.at)
Goded Shahaf and Shimon Marom. Learning in networks of cortical neurons. J. of Neuroscience [volume 21(22):8782–8788, Nov. 15 (2001)
Schultz W. Predictive reward signal of dopamine neurons. J Neurophysiol, 80:1–27 (1998)
Danny Eytan and Shimon Marom. Learning in Ex-Vivo Developing Networks of Cortical Neurons Progress in Brain Research, Volume 147, “Development, Dynamics and Pathology of neural Networks”, van Pelt et al, Editors, (2004)
Aviel Y., Pavlov E., Abeles M., and Hom D. Synfire chain in a balanced network. Neurocomp. 44:285–292 (2002)
Ikegaya Y., Aaron G., Cossart R., Aronov D., Lampl I., Ferster D., Yuste R., Synfire Chains and Cortical Songs: Temporal Modules of Cortical Activity. Science. 304(5670): 559–564, (2004)
Prashant Joshi. Synthesis of a liquid machine with Hopefield/Brody transient synchrony. M.SC Thesis, (2002)
I. Raichelgauz, K. Odinaev and Y.Y. Zeevi, “Closed-Loop Liquid Neural Architectures”, Neurocomputing (Invited Paper), 2005 (in press).
DeMarse T., Cadotte A., Douglas P., He P., Trinh V., Computation Within Cultured Neural Networks, Proceedings of the 26th Annual International Conference of the IEEE EMBS, (2004)
Unger H., Zeevi Y. Y., Blind Separation of Spatio-temporal Data Sources. ICA 2004: 962–969 (2004)
M. Abeles, I. Gat, Detecting precise firing sequences in experimental data, Journal of Neuroscience Methods, Vol. 107, Issues 1–2, pp. 141–154 (2001)
Abeles M., Neural Circuits of the Cerebral Cortex, Cambridge University Press (1991)
Yuste, R., Lanni, F. and Konnerth, A., Imaging Neurons: a Laboratory Manual, Cold Spring Harbor Press, (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Odinaev, K., Raichelgauz, I., Zeevi, Y.Y. (2006). Mapping of Natural Patterns by Liquid Architectures Implementing Neural Cliques. In: Tiwari, A., Roy, R., Knowles, J., Avineri, E., Dahal, K. (eds) Applications of Soft Computing. Advances in Intelligent and Soft Computing, vol 36. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-36266-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-540-36266-1_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-29123-7
Online ISBN: 978-3-540-36266-1
eBook Packages: EngineeringEngineering (R0)