Abstract
The paper describes a new concept for training the neural networks, which can be concretized by using a new modified classical architecture. The idea considered to be the basis of this new architecture was taken over from learning machine, namely that for defining a concept, we need both negative and positive examples. Neural networks are models that are trained only with positive examples and allow the recognition of new examples using the learning machine. Training neural networks with negative examples aims at preventing the development of some specific features of these examples and at obtaining a better recognition of the positive examples. The architecture developed through this method is generic and can be applied to any type of neural network. For simplicity and for the need of obtaining immediate results, a multilayer perceptron was chosen for testing. The results achieved with the help of this network are encouraging and they open new possibilities of study for the future.
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
STeodorean Gavril, “Artificial Neural Networks”, Ed. Cluj-Napoca, 1995
Negnevitsky, M. “Artificial Intelligence: A Guide to Intelligent Systems” (2nd Edition), Addison Wesley, England, 2005.
Bratko I. “PROLOG - Programming for Artificial Intelligence” (2nd Edition) Addison Wesley, England,1993.
Russell S., Norvig P. - “Artificial Intelligence : A Modern Approach” (Second Edition), Prentice Hall,2003.
Luger G. - “Artificial Intelligence :Structures and Strategies for Complex Problem Solving” (Fifth Edition) Addison Wesley, 2005.
NIST Handprinted Forms and Characters Database, www.nist.gov/ srd/ nistsd19.htm, 2007.
Mitchell, T.M. - “Version spaces - an approach to concept learning”, Report No. STAN-CS-78-711,Computer Science Dept., Stanford University, 1978.
Mitchell, T.M. - “An analysis of generalization as a search problem”, Proceedings IJCAI,6, 1979.
Mitchell, T.M. - “Generalization as search. Artificial Intelligence”, 18(2):203-226, 1982
Quinlan, J.R. - “Induction of decision trees. Machne Learning”, 1(1):81-106, 1982
Shannon, C. - “A mathematical theory of communication.”, Bell System Technical Journal,27:379-423, 1948
Winston, P. H. - “Learning structural descriptions from examples”, In P.H. Winston editor, 1975
Winston, P. H. - “The psychology of Computer Vision ”, New York, McGraw-Hill, 1975
Winston, P. H. - “Artificial Intelligence”, 3rd edition Reading, MA:Addison Wesley, 1992
Sejnowski, T. J. and Rosenberg, C. R.- “Parallel networks that learn to pronounce English text.”, Complex Systems, 1:145-168, 1987
Hecht-Nielsen, R. - “Counterpropagation networks”, Applied Optics, 26:4979-4984, 1984
Qun Z., Principe J.C. - “Incorporating virtual negative examples to improve SAR ATR”, Proceedings of the SPIE - The International Society for Optical Engineering, v 4053, 2000, 354-360
Principe J.C., Dongxin X., Qun Z. - “Learning from examples with information theoretic criteria”, Journal of VLSI Signal Processing System for Signal, Image and Video Technology, v 26, 2000, 61-77
Qun Z., Principe J.C. - “Improve ATR performance by incorporating virtual negative examples”, Proceedings of the International Joint Conference on Neural Networks, 1999, 3198-3203
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science+Business Media B.V.
About this paper
Cite this paper
CernĂZanu-GlĂvan, C., Holban, Ş. (2008). Improving Neural Network Performances - Training with Negative Examples. In: Sobh, T., Elleithy, K., Mahmood, A., Karim, M.A. (eds) Novel Algorithms and Techniques In Telecommunications, Automation and Industrial Electronics. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-8737-0_10
Download citation
DOI: https://doi.org/10.1007/978-1-4020-8737-0_10
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-8736-3
Online ISBN: 978-1-4020-8737-0
eBook Packages: EngineeringEngineering (R0)