Abstract
This paper proposes a new error back propagation learning algorithm that properly enhances the sensitivity of input and output mapping by applying a high-pass filter characteristic to the conventional error back propagation learning algorithm, allowing small input feature variations to be successfully indicated. For the sensitive discrimination of novel class data with slightly different characteristics from the normal class data, the cost function in the proposed neural network algorithm is modified by further increasing the input and output sensitivity, where weight update rules are used to minimize the cost function using a gradient descent method. The proposed algorithm is applied to an auto-associative multilayer perceptron neural network and its performance evaluated with two real-world applications: a laser spot detection-based computer interface system for detecting a laser spot in complex backgrounds and an automatic inspection system for the reliable detection of Mura defects that occur during the manufacture of flat panel liquid crystal displays. When compared with the conventional error back propagation learning algorithm, the proposed algorithm shows a better performance as regards detecting small input feature variations by increasing the input–output mapping sensitivity.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Skitt PJC, Javed MA, Sanders SA, Higginson AM (1993) Process monitoring using auto-associative, feed-forward artificial neural networks. J Intell Manuf 4(1):79–94
Chen FL, Liu SF (2000) A neural-network approach to recognize defect spatial pattern in semiconductor fabrication. IEEE Trans Semiconduct Manufact 13(3):366–373
Su CT, Yang T, Ke CM (2002) A neural-network approach for semiconductor wafer post-sawing inspection. IEEE Trans Semiconduct Manufact 15(2):260–266
Marwala T, Chakraverty S (2006) Fault classification in structures with incomplete measured data using auto associative neural networks and genetic algorithm. Curr Sci 90(4):542–548
Pramodh C, Ravi V (2007) Modified great deluge algorithm based auto associative neural network for bankruptcy prediction in banks. Int J Comput Intell Res 3(4):363–370
Chen LF, Su CT, Chen MH (2009) A neural–network approach for defect recognition in TFT-LCD photolithography process. IEEE Trans Electron Packag Manuf 32(1):1–8
Drucker H, Cun YL (1992) Inproving generalization performance using double back propagation. IEEE Trans Neural Netw 3(6):991–997
Chong SY, Tino P, Yao X (2008) Measuring generalization performance in coevolutionary learning. IEEE Trans Evol Comput 12(4):479–505
Jung C, Ban S-W, Jeong S, Lee M (2010) Input and output mapping sensitive auto-associative multilayer perceptron for computer interface system based on image processing of laser pointer spot. In: Proceedings of the 17th international conference on neural information processing (ICONIP), pp 185–192
Haykin S (1998) Neural networks: a comprehensive foundation, 2nd edn. Prentice Hall International, NJ
Carsten K, Heinrich M (1998) Interaction with a projection screen using a camera-tracked laser pointer. In: Proceedings of the international conference on multimedia modeling. IEEE Computer Society Press, pp 191–192
Olsen Jr DR, Nielsen T (2001) Laser pointer interaction. In: Proceedings of the SIGCHI conference on Human factors in computing systems, pp 17–22
Lapointe JF, Godin G (2005) On-screen laser spot detection for large display interaction. In: Proceedings of the IEEE international work on haptic audio environments and their applications, pp 72–76
Lim JG, Sharifi F, Kwon D (2008) Fast and reliable camera-tracked laser pointer system designed for audience. In: Proceedings of the 5th international conference on ubiquitous robots and ambient intelligence, pp 529–534
Kim N, Lee S, Lee J, Lee B (2008) Laser pointer interaction system based on image processing. J Korea Multimed Soc 11(3):373–385
Jung C, Lee M (2011) Laser spot pattern recognition based computer interface using I/O mapping sensitive neural networks. Will be published (ICCE)
Bradski GR, Kaehler A (2008) Learning OpenCV: computer vision with the OpenCV library. O`Reilly Media, Sebastopol
Jolliffe IT (2002) Principal component analysis series: springer series in statistics, 2nd edn. Springer, NY
Weber C, Moslehi B, Dutta M (1995) An integrated framework for yield management and defect/fault reduction. IEEE Trans Semiconduct Manufact 8(2):110–120
Zhang JM, Lin RM, Wang MJJ (1999) The development of an automatic post-sawing inspection system using computer vision techniques. Comput Ind 40(1):51–60
Chou PB, Rao AR, Sturzenbecker MC, Wu FY, Brecher VH (1997) Automatic defect classification for semiconductor manufacturing. Mach Vision Appl 9(4):210–214
Acknowledgments
This research was financially supported by the Ministry of Education, Science Technology (MEST) and Korea Institute for Advancement of Technology (KIAT) through the Human Resource Training Project for Regional Innovation.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jung, C., Kim, CS., Ban, SW. et al. Novel input and output mapping-sensitive error back propagation learning algorithm for detecting small input feature variations. Neural Comput & Applic 21, 705–713 (2012). https://doi.org/10.1007/s00521-011-0649-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-011-0649-8