Abstract
A large class of problems requires real-time processing of complex temporal inputs in real-time. These are difficult tasks for state-of-the-art techniques, since they require capturing complex structures and relationships in massive quantities of low precision, ambiguous noisy data. 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. We extend the computational power of this framework by closing the loop. This is accomplished by applying, in parallel to the supervised learning of the readouts, a biologically-realistic learning within the framework of the microcircuit. This approach is inspired by neurobiological findings from ex-vivo multi-cellular electrical recordings and injection of dopamine to the neural culture. We show that by closing the loop we obtain a much more effective performance with the new Co-Evolutionary Liquid Architecture. We illustrate the added value of the closed-loop approach to liquid architectures by executing a speech recognition task.
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
Maass, W., Natschläger, T., Markram, H.: Real-time computing without stable states: A new framework for neural computation based on perturbations. Neural Computation 14(11), 2531–2560 (2002)
Maass, W., Natschläger, T., Markram, H.: Computational models for generic cortical microcircuits. In: Feng, J. (ed.) Computational Neuroscience: A Comprehensive Approach, ch. 18, pp. 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. 14(2), 139–147 (2004)
Eytan, D., Minerbi, A., Ziv, N., Marom, S.: Dopamine-induced Dispersion of Correlations Between Action Potentials in Networks of Cortical Neurons. J. Neurophysiol. 92, 1817–1824 (2004)
Silberberg, G., Gupta, A., Markram, H.: Stereotypy in neocortical microcircuits. Trends Neurosci. 25(5), 227–230 (2002)
Tsodyks, M., Pawelzik, K., Markram, H.: Neural networks with dynamic synapses. Neural Computation 10, 821–835 (1998)
Natschläger, T., Markram, H., Maass, W.: Computer models and analysis tools for neural microcircuits. In: Kötter, R. (ed.) A Practical Guide to Neuroscience Databases and Associated Tools, ch. 9. Kluver Academic Publishers, Boston (2002) (in press), http://www.lsm.tugraz.at
Shahaf, G., Marom, S.: Learning in networks of cortical neurons. J. of Neuroscience 21(22), 8782–8788 (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. In: van Pelt, et al. (eds.) Development, Dynamics and Pathology of neural Networks, vol. 147 (2004)
Hopfield, J., Brody, C.: The mus silicium (sonoran desert sand mouse) web page. Base: http://moment.princeton.edu/~mus/Organism
Hopfield, J., Brody, C.: What is a moment? Transient synchrony as a collective mechanism for spatiotemporal integration. Proc. Natl. Acad. Sci. USA 98(3), 1282–1287 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Raichelgauz, I., Odinaev, K., Zeevi, Y.Y. (2005). Co-evolutionary Learning in Liquid Architectures. In: Cabestany, J., Prieto, A., Sandoval, F. (eds) Computational Intelligence and Bioinspired Systems. IWANN 2005. Lecture Notes in Computer Science, vol 3512. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11494669_30
Download citation
DOI: https://doi.org/10.1007/11494669_30
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26208-4
Online ISBN: 978-3-540-32106-4
eBook Packages: Computer ScienceComputer Science (R0)