Advertisement

How Neural Networks (NN) Can (Hopefully) Learn Faster by Taking into Account Known Constraints

  • Chitta Baral
  • Martine Ceberio
  • Vladik KreinovichEmail author
Chapter
  • 10 Downloads
Part of the Studies in Systems, Decision and Control book series (SSDC, volume 276)

Abstract

Neural networks are a very successful machine learning technique. At present, deep (multi-layer) neural networks are the most successful among the known machine learning techniques. However, they still have some limitations, One of their main limitations is that their learning process still too slow. The major reason why learning in neural networks is slow is that neural networks are currently unable to take prior knowledge into account. As a result, they simply ignore this knowledge and simulate learning “from scratch”. In this paper, we show how neural networks can take prior knowledge into account and thus, hopefully, learn faster.

Notes

Acknowledgements

This work was supported in part by NSF grants HRD-0734825, HRD-1242122, and DUE-0926721, and by an award from Prudential Foundation.

References

  1. 1.
    Bishop, C.M.: Pattern Recognition and Machine Learning. Springer, N.Y. (2006)zbMATHGoogle Scholar
  2. 2.
    Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Chitta Baral
    • 1
  • Martine Ceberio
    • 2
  • Vladik Kreinovich
    • 2
    Email author
  1. 1.Department of Computer ScienceArizona State UniversityTempeUSA
  2. 2.Department of Computer ScienceUniversity of Texas at El PasoEl PasoUSA

Personalised recommendations