Abstract
Isotropic Sequence Order learning (ISO-learning) and Input Correlation Only learning (ICO-learning) are unsupervised neural algorithms to learn temporal differences. The use of devices implementing this algorithms by simulation in reactive neural networks is proposed. We have applied several modifications to original rules: weights sign restriction, to adequate ISO-learning and ICO-learning devices outputs to the usually predefined kinds of connections (excitatory/inhibitory) used in neural networks, and decay term inclusion for weights stabilization. Original experiments with these algorithms are replicated as accurate as possible with a simulated robot and a discretization of the algorithms. Results are similar to those obtained in original experiments with analogue devices.
This is a preview of subscription content, log in via an institution to check access.
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
Oppenheim, A.V., Willsky, A.S., Nawab, S.H.: Signals and systems, 2nd edn. Prentice-Hall, Englewood Cliffs (Aug. 1996)
Braitenberg, V.: Vehicles: experiments in synthetic psychology. MIT Press, Cambridge (1986)
Gerstner, W., Kistler, W.M.: Mathematical formulations of Hebbian learning. Biological Cybernetics 87, 404–415 (2002)
Kempter, R., Gerstner, W., van Hammen, L.L.: Intrinsic stabilization of output rates by spike-based Hebbian learning. Neural Computation 13, 2709–2741 (2001)
Porr, B., von Ferber, C., Wörgötter, F.: ISO-learning aproximates a solution to the inverse-controller problem in an unsupervised behavioural paradigm. Neural Computation 15, 865–884 (2003)
Porr, B., Wörgötter, F.: Isotropic sequence order learning. Neural Computation 15, 831–864 (2003)
Porr, B., Wörgötter, F.: Isotropic sequence order learning in a closed-loop behavioural system. Roy. Soc. Phil. Trans. Mathematical, Physical & Engineering Sciences 361(1811), 2225–2244 (2003)
Porr, B.: Sequence-Learning in a Self-Referential Closed-Loop Behavioural System. PhD thesis, Stirling University (May 2003)
Porr, B., Wörgötter, F.: Temporal Hebbian learning in rate-coded neural networks: A theoretical approach towards classical conditioning. In: Dorffner, G., Bischof, H., Hornik, K. (eds.) ICANN 2001. LNCS, vol. 2130, pp. 1115–1120. Springer, Heidelberg (2001)
Porr, B., Wörgötter, F.: Strongly improved stability and faster convergence of temporal sequence learning by utilising input correlations only. Neural Computation 18(6), 1380–1412 (2006)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Cuadra Troncoso, J.M., Álvarez Sánchez, J.R., de la Paz López, F. (2007). Discretization of ISO-Learning and ICO-Learning to Be Included into Reactive Neural Networks for a Robotics Simulator. In: Mira, J., Álvarez, J.R. (eds) Nature Inspired Problem-Solving Methods in Knowledge Engineering. IWINAC 2007. Lecture Notes in Computer Science, vol 4528. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73055-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-540-73055-2_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73054-5
Online ISBN: 978-3-540-73055-2
eBook Packages: Computer ScienceComputer Science (R0)