Abstract
This chapter provides a description of learning methods for artificial intelligence algorithms. It presents selected information on supervised learning algorithms that constitute a group of the most preferred NN learning methods that are applied to problems where the values of approximate representations are known. These algorithms are characterized by a fast learning rate, accurate mapping of desired signals and a simple notation as opposed to other learning methods.
This is a preview of subscription content, log in via an institution to check access.
References
Barto, A., Sutton, R.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Barto, A., Mahadevan, S.: Recent advances in hierarchical reinforcement learning. Discret. Event Dyn. Syst. 13, 343–379 (2003)
Cichosz, P.: Learning Systems (in Polish). WNT, Warsaw (2000)
Dias, F.M., et al.: Using the Levenberg–Marquardt for on–line training of a variant system. Lecture Notes in Computer Science, vol. 3697, pp. 359–364 (2005)
Hagen, S., Krose, B.: Neural Q-learning. Neural Comput. Appl. 12, 81–88 (2003)
Jamshidi, M., Zilouchian, A.: Intelligent Control Systems Using Soft Computing Methodologies. CRC Press, London (2001)
Osowski, S.: Neural Networks (in Polish). Warsaw University of Technology Publishing House, Warsaw (1996)
Osowski, S.: Neural Networks - An Algorithmic Approach (in Polish). WNT, Warsaw (1996)
Rutkowski, L.: Computational Intelligence - Methods and Techniques (in Polish). Polish Scientific Publishers PWN, Warsaw (2005)
Stadnicki, J.: Theory and Practice of Optimization Task Solving (in Polish). WNT, Warsaw (2006)
Watkins, C.: Learning from delayed rewards. Ph.D. thesis, Cambridge University, Cambridge, England (1989)
Wilamowski, B., Kaynak, O.: An algorithm for fast convergence in training neural networks. In: Proceedings of IJCNN, vol. 3, pp. 1178–1782 (2001)
Zelinsky, A., Gaskett, C., Wettergreen, D.: Q-learning in continuous state and action spaces. In: Proceedings of the Australian Joint Conference on Artificial Intelligence, pp. 417–428. Springer, Berlin (1999)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this chapter
Cite this chapter
Szuster, M., Hendzel, Z. (2018). Learning Methods for Intelligent Systems. In: Intelligent Optimal Adaptive Control for Mechatronic Systems. Studies in Systems, Decision and Control, vol 120. Springer, Cham. https://doi.org/10.1007/978-3-319-68826-8_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-68826-8_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68824-4
Online ISBN: 978-3-319-68826-8
eBook Packages: EngineeringEngineering (R0)