Advertisement

Contextual Binding: A Deductive Apparatus in Artificial Neural Networks

  • Jim Q. Chen
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 70)

Abstract

The Artificial neural networks are key mechanisms in artificial intelligence, especially in machine learning. A close examination of this mechanism reveals some philosophical challenges in the current approach. With all the emphasis on the techniques used in the mining of the great volume of datasets collected and available, inductive reasoning is well employed to find out characteristics and identify patterns. However, deductive reasoning is not sufficiently utilized. In order to bring the current approach to the right track, this paper proposes a novel approach in which a deductive apparatus is made use of. This deductive apparatus is built on contextual binding, which sets a priority and provides guidance for the processing of various types of datasets collected and available, thus making the processing efficient and effective. The benefits and implementation of this new approach are also discussed.

Keywords

Artificial neural networks Machine learning Inductive method Deductive method Contextual binding 

References

  1. 1.
    Schmidhuber, J.: Deep learning in neural networks: an overview. Technical Report IDSIA-03-14, the Swiss AI Lab IDSIA, University of Lugano & SUPSI, Switzerland (2014)Google Scholar
  2. 2.
    Klauer, K., Phye, G.: Inductive reasoning: a training approach. Rev. Educ. Res. 78(1), 85–123 (2008).  https://doi.org/10.3102/0034654307313402CrossRefGoogle Scholar
  3. 3.
    Dormehl, L.: What is an artificial neural network? Here’s everything you need to know. Emerging Tech, Digital Trends, May 11, 2018. https://www.digitaltrends.com/cool-tech/what-is-an-artificial-neural-network/. Last accessed 2 July 2018
  4. 4.
    The Center for Academic Success at Butter College: Deductive, inductive and abductive reasoning, http://www.butte.edu/departments/cas/tipsheets/thinking/reasoning.html. Last accessed 10 May 2018
  5. 5.
    Gardner, H.: Frames of Mind: The Theory of Multiple Intelligences, 3rd edn. Basic Books, London (2011)Google Scholar
  6. 6.
    Bradford, A.: The five (and more) senses. Livescience, October 23, 2017. https://www.livescience.com/60752-human-senses.html. Last accessed 28 May 2018
  7. 7.
    Taylor, M.: Neural Networks Math: A Visual Introduction for Beginners. Blue Windmill Media (2017)Google Scholar
  8. 8.
    Beebe, N.: Digital forensic research: the good, the bad and the unaddressed. In: Peterson, G., Shenoi, S. (eds.) Advances in Digital Forensics, vol. V, pp. 17–36. Springer, Berlin (2009)CrossRefGoogle Scholar
  9. 9.
    Marti, R., Reinelt, G.: Heuristic methods. In: Marti, R., Reinelt, G. (eds.) The Linear Ordering Problem: Exact and Heuristic Methods in Combinatorial Optimization 175, pp. 17–40. Springer, Berlin (2011).  https://doi.org/10.1007/978-3-642-16729-4_2CrossRefzbMATHGoogle Scholar
  10. 10.
    Chen, J.: On contextual binding and its application in cyber deception detection. In: Proceedings of the 2015 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, pp. 215–218. IEEE, New York (2015)Google Scholar
  11. 11.
    Chen, J.: Contextual binding and intelligent targeting. In: Proceedings of the 2016 IEEE/WIC/ACM International Conference on Web Intelligence, pp. 701–704. IEEE, New York (2016)Google Scholar
  12. 12.
    Chen, J.: An intelligent path toward accurate attribution. In: Proceedings of the 2018 IEEE/SAI Computing Conference, pp. 1134–1139. IEEE, New York (2018)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Jim Q. Chen
    • 1
  1. 1.National Defense UniversityWashingtonUSA

Personalised recommendations