Abstract
A reinforced search algorithm for the stochastic feedforward neural networks is described. A stochastic neuron is used in a network as a searching unit. Reinforcement signal from environment is used for weights and variance adaptation. This is experimentally compared with more traditional techniques like gradient-based learning algorithm and evolutionary algorithm.
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
Barto. A. (1997) Reinforcement learning in Neural Systems for Control, Academic Press
Gullapalli, V. (1990) A Stochastic Reinforcement Learning Algorithm for Learning Real-Valued Functions. Neural Network 3:671–692
Haykin, S. (1999) Neural Networks: A Comprehensive Foundation, 2nd edition, Prentice Hall, New Jersey
Hassoum, M. H. (1995) Fundamentals of Artificial Neural Networks, MIT Press
Hinton, G. E., Sejnovski, T. J. (1986) Learning and Re-learning in Boltzmann Machines, PDP, MTI Press
Markram, H., Lubke, J., Frotscher, M., Sakmann, B. (1997) Regulation of synaptic efficacy by Coincidence of postsynaptic APs and EPSPs, Science, 213–215
Muller, J. J., Reinhardt, J., Strickland, M. T. (1995) Neural Network. An Introduction, Springer-Verlag, Berlin Heidelberg
Šter, B., (1999) Reinforced Learning with Neural Networks in Control Problems, Ph.D Thesis, University of Ljubljana
Torndike, E. L., (1911) Animal Inteligence, Hafher, Darien, Conn
Vavpotič, S., Dobnikar, A., (2002) Speeding up Execution of Evolutionary Algorithms with Multiprocessor and Multicomputer Systems, Electrotechnical Review 69(3–4): 227–233
Williams, R. J. (1992) Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning, Machine Learning 8: 229–256
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Wien
About this paper
Cite this paper
Trebar, M., Dobnikar, A. (2003). Reinforced Search in Stochastic Neural Network. In: Pearson, D.W., Steele, N.C., Albrecht, R.F. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-0646-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-7091-0646-4_9
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-00743-3
Online ISBN: 978-3-7091-0646-4
eBook Packages: Springer Book Archive