Neural Computing and Applications

, Volume 18, Issue 4, pp 309–320 | Cite as

Application of an emotional neural network to facial recognition

Original Article

Abstract

In our attempts to model human intelligence by mimicking the brain structure and function, we overlook an important aspect in human cognition, which is the emotional factor. It may currently sound unthinkable to have emotional machines; however, it is possible to simulate certain artificial emotions with the aim of improving machine learning. This paper investigates the efficiency of an emotional neural network, which uses a modified back propagation learning algorithm. The modifed algorithm, namely the emotional BP learning algorithm, has two emotional parameters, anxiety and confidence, that are modeled during machine learning and decision making. The emotional neural network will be implemented to a facial recognition problem using images of faces with different orientations and contrast levels, and its performance will be compared to that of a conventional neural network. Experimental results suggest that artificial emotions can be successfully modeled and efficiciently implemented to improve neural networks learning and generaliztion.

Keywords

Neural networks Back propagation algorithm Artificial emotion modeling Facial recognition 

References

  1. 1.
    Levine DS (2007) Neural network modeling of emotion. Phys Life Rev 4:37–63. doi:10.1016/j.plrev.2006.10.001 CrossRefGoogle Scholar
  2. 2.
    Lewin DI (2001) Why is that computer laughing? IEEE Intell Syst 16(5):79–81Google Scholar
  3. 3.
    Picard RW (1997) Affective computing. MIT Press, CambridgeGoogle Scholar
  4. 4.
    Yoon J, Park S, Kim J (2004) Emotional robotics based on iT_Media. In: Proceedings of the 30th annual conference of the IEEE Industrial Electronics Society, Busan, Korea, November 2–6, 2004, pp 3148–3153Google Scholar
  5. 5.
    Boehner K, DePaula R, Dourish P, Sengers P (2007) How emotion is made and measured. Int J Hum Comput Stud 65:275–291. doi:10.1016/j.ijhcs.2006.11.016 CrossRefGoogle Scholar
  6. 6.
    Anderson ML (2005) Why is AI so scary? Artif Intell 169:201–208. doi:10.1016/j.artint.2005.10.008 CrossRefGoogle Scholar
  7. 7.
    Bates J (1994) The role of emotion in believable agents. Commun ACM 37(7):122–125. doi:10.1145/176789.176803 CrossRefGoogle Scholar
  8. 8.
    Perlis D (2005) Review of “Hawkins on intelligence: fascination and frustration” by Jeff Hawkins and Sandra Blakeslee, Times Books, 2004. Artif Intell 169:184–191. doi:10.1016/j.artint.2005.10.012 CrossRefMathSciNetGoogle Scholar
  9. 9.
    Cooke DE (2007) Examining artificial and human intelligence. IEEE Intell Syst 22(2):93. doi:10.1109/MIS.2007.23 CrossRefMathSciNetGoogle Scholar
  10. 10.
    Martinez-Miranda J, Aldea A (2005) Emotions in human and artificial intelligence. Comput Hum Behav 21:323–341. doi:10.1016/j.chb.2004.02.010 CrossRefGoogle Scholar
  11. 11.
    Ortony A, Clore GL, Collins A (1988) The cognitive structure of emotions. Cambridge University Press, CambridgeGoogle Scholar
  12. 12.
    Ushida H, Hirayama Y, Nakajima H (1998) Emotion model for life-like agent and its evaluation. In: Proceedings of the 15th national/10th conference on Artificial Intelligence/Innovative applications of artificial intelligence, Madison, July 1998. American Association for Artificial Intelligence, Menlo Park, pp 62–69Google Scholar
  13. 13.
    El-Nasr MS, Yen J, Ioerger TR (2000) FLAME—fuzzy logic adaptive model of emotions. Auton Agent Multi Agent Syst 3:219–257CrossRefGoogle Scholar
  14. 14.
    Gratch J (2000) Modeling the interplay between emotion and decision making. In: Proceedings of the ninth conference on computer generated forces and behavioral representation, Orlando, May 2000Google Scholar
  15. 15.
    Kort B, Reilly R, Picard RW (2001) An affective model of interplay between emotions and learning: reengineering educational pedagogy—building learn companion. In: IEEE international conference on advanced learning technologies (ICALT 2001), Madison, 6–8 August 2001, pp 43–48Google Scholar
  16. 16.
    Poel M, den Akker R, Nijholt A, van Kesteren AJ (2002) Learning emotions in virtual environments. In: Trappl R (ed) Proceedings of the sixteenth European meeting on cybernetics and system research (Vienna, 2–5 April 2002), vol. 2, pp 751–756Google Scholar
  17. 17.
    Doya K (2002) Meta-learning and neuro-modulation. Neural Netw 15(4–6):495–506CrossRefGoogle Scholar
  18. 18.
    Clocksin WF (2004) Memory and emotion in the cognitive architecture. In: Davis D (ed) Visions of mind. IDEA Group Publishing, Hershey, pp 122–139Google Scholar
  19. 19.
    Rousseau D, Hayes-Roth B (1997) Improvisational synthetic actors with flexible personalities. Research report KSL 97-10. Knowledge Systems Laboratory, Stanford University, StanfordGoogle Scholar
  20. 20.
    Canamero D (2003) Designing emotions for activity selection in autonomous agents. In: Trappl R, Petta P, Payr S (eds) Emotions in humans and artifacts. MIT Press, CambridgeGoogle Scholar
  21. 21.
    Abu Maria K, Abu Zitar R (2007) Emotional agents: a modeling and an application. Inf Softw Technol 49:695–716. doi:10.1016/j.infsof.2006.08.002 CrossRefGoogle Scholar
  22. 22.
    Gobbini MI, Haxby JV (2007) Neural systems for recognition of familiar faces. Neuropsychologia 45:32–41. doi:10.1016/j.neuropsychologia.2006.04.015 CrossRefGoogle Scholar
  23. 23.
    Khashman A (2008) A modified back propagation learning algorithm with added emotional coefficients. IEEE Trans Neural Netw 19(11):1896–1909CrossRefGoogle Scholar
  24. 24.
    Khashman A (2006) Face recognition using neural networks and pattern averaging. Lect Notes Comput Sci 3972:98–103CrossRefGoogle Scholar
  25. 25.
    Khashman A (2007) Intelligent global face recognition. In: Delac K, Grgic M (eds) Face recognition. ITECH Education and Publishing, Vienna, Chapter 11, ISBN 978-3-902613-03-5Google Scholar
  26. 26.
    Rumelhart D, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In: Rumelhart D, McClelland J (eds) Parallel distributed processing, vol 1. MIT Press, CambridgeGoogle Scholar
  27. 27.
    Baumgartner T, Esslen M, Jancke L (2006) From emotion perception to emotion experience: emotions evoked by pictures and classical music. Int J Psychophysiol 60:34–43. doi:10.1016/j.ijpsycho.2005.04.007 CrossRefGoogle Scholar
  28. 28.
    Khashman A (2006) Intelligent face recognition: local versus global pattern averaging. Lect Notes Artif Intell 4304:956–961Google Scholar

Copyright information

© Springer-Verlag London Limited 2008

Authors and Affiliations

  1. 1.Department of Electrical and Electronic EngineeringIntelligent Systems Research Group (ISRG), Near East UniversityMersin 10Turkey

Personalised recommendations