Abstract
The paper addresses the problem of modeling highly nonlinear mappings of contextual nature with neural nets. The model of context-dependent multilayer neural net is recalled, along with basic training algorithms. Although the effectiveness of context-dependent nets has been proved theoretically, the lack of efficient and simple training algorithm implementations suppressed popularity of this neural net model.
In this paper efficient conjugate gradient training algorithms for context-dependent nets are developed and discussed, as well as illustrated with classification and regression problem.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Berthouze, L., Tijsseling, A.: A Neural Model for Context-Dependent Sequence Learning. Neural Processing Letters 23, 27–45 (2006)
Ciskowski, P.: Learning of Context-Dependent Neural Nets, Ph.D. thesis, Wroclaw University of Technology (July 2002)
Ciskowski, P., Rafajlowicz, E.: Context-Dependent Neural Nets - Structures and Learning. IEEE Transactions on Neural Networks 15(6), 1367–1377 (2004)
Ciskowski, P.: Contextual Modeling Using Context-Dependent Feedforward Neural Nets. In: Blackburn, P., Ghidini, C., Turner, R.M., Giunchiglia, F. (eds.) CONTEXT 2003. LNCS, vol. 2680, pp. 435–442. Springer, Heidelberg (2003)
Hagan, M.T., Demuth, H.B., Beale, M.H.: Neural Network Design. PWS Publishing, Boston (1996)
Penrose, K., Nelson, A., Fisher, A.: Generalized Body Composition Prediction Equation for Men Using Simple Measurement Techniques. Medicine and Science in Sports and Exercise 17(2), 189 (1985)
Arritt, R.P., Turner, R.M.: Context-Sensitive Weights for a Neural Network. In: Blackburn, P., Ghidini, C., Turner, R.M., Giunchiglia, F. (eds.) CONTEXT 2003. LNCS, vol. 2680, pp. 29–39. Springer, Heidelberg (2003)
Turney, P.: The Identification of Context-Sensitive Features: A Formal Definition of Context for Concept Learning. In: 13th International Conference on Machine Learning (ICML 1996), Workshop on Learning in Context-Sensitive Domains, Bari, Italy, pp. 53–59 (1996)
Turney, P.: The Management of Context-Sensitive Features: A Review of Strategies. In: 13th International Conference on Machine Learning (ICML 1996), Workshop on Learning in Context-Sensitive Domains, Bari, Italy, pp. 60–66 (1996)
Watrous, R., Towell, G.: A Patient-Adaptive Neural Network ECG Patient Monitoring Algorithm. In: Computers in Cardiology, Vienna, Austria, September 10-13, pp. 10–13 (1995)
Yeung, D.T., Bekey, G.A.: Using a Context-Sensitive Learning for Robot Arm Control. In: IEEE International Conference on Robotics and Automation, Scottsdale, Arizona, May 14-19, pp. 1441–1447 (1989)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Ciskowski, P. (2014). Efficient Training of Context-Dependent Neural Nets with Conjugate Gradient Algorithms. In: Zamojski, W., Mazurkiewicz, J., Sugier, J., Walkowiak, T., Kacprzyk, J. (eds) Proceedings of the Ninth International Conference on Dependability and Complex Systems DepCoS-RELCOMEX. June 30 – July 4, 2014, Brunów, Poland. Advances in Intelligent Systems and Computing, vol 286. Springer, Cham. https://doi.org/10.1007/978-3-319-07013-1_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-07013-1_14
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07012-4
Online ISBN: 978-3-319-07013-1
eBook Packages: EngineeringEngineering (R0)