Skip to main content
SpringerLink
Log in

Finding MAPs Using High Order Recurrent Networks

  • Conference paper
Neural Information Processing (ICONIP 2009)

Part of the book series: Lecture Notes in Computer Science ((LNTCS,volume 5863))

Included in the following conference series:

  • 1425 Accesses

Abstract

Belief revision is the problem of finding the most plausible explanation for an observed set of evidences. This has many applications in various scientific domains like natural language understanding, medical diagnosis and computational biology. Bayesian Networks (BN) is an important probabilistic graphical formalism used widely for belief revision tasks. In BN, belief revision can be achieved by setting the values of all random variables such that their joint probability is maximized. This assignment is called the maximum a posteriori (MAP) assignment. Finding MAP is an NP-Hard problem. In this paper, we are proposing finding the MAP assignment in BN using High Order Recurrent Neural Networks through an intermediate representation of Cost-Based Abduction. This method will eliminate the need to explicitly construct the energy function in two steps, objective and constraints, which will decrease the number of free parameters to set.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 129.00
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. McCarthy, J., Hayes, P.J.: Some Philosophical Problems from the Standpoint of Artificial Intelligence. In: Meltzer, B., Michie, D. (eds.) Machine Intelligence, vol. 4, pp. 463–502. Edinburgh University Press (1969)

    Google Scholar 

  2. Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann, San Francisco (1988)

    Google Scholar 

  3. Abdelbar, A.M.: Designing high order recurrent networks for Bayesian belief revision. In: Medsker, L.R., Jain, L.C. (eds.) Recurrent Neural Networks: Design and Applications, pp. 77–98. CRC Press, Boca Raton (1999)

    Google Scholar 

  4. Shimony, S.E.: Finding MAPs for belief networks is NP-hard. Artificial Intelligence 68, 399–410 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  5. Abdelbar, A.M., Hedetniemi, S.M.: Approximating MAPs for belief networks is NP-hard and other theorems. Artificial Intelligence 102, 21–38 (1998)

    Article  MATH  MathSciNet  Google Scholar 

  6. Abdelbar, A.M.: An algorithm for finding MAPs for belief networks through cost-based abduction. Artificial Intelligence 104, 331–338 (1998)

    Article  MathSciNet  Google Scholar 

  7. Abdelbar, A.M., Andrews, E.A.M., Wunsch II, D.C.: Abductive Reasoning with Recurrent Neural Networks. Neural Networks 16(5-6), 665–673 (2003)

    Article  Google Scholar 

  8. Abdelbar, A.M., El-Hemely, M.A., Andrews, E.A.M., Wunsch II, D.C.: Recurrent Neural Networks with Backtrack-Points and Negative Reinforcement Applied to Cost-Based Abduction. Neural Networks 18(5-6), 755–764 (2005)

    Article  MATH  Google Scholar 

  9. Charniak, E., Shimony, S.E.: Probabilistic semantics for cost-based abduction. In: AAAI National Conference on Artificial Intelligence, pp. 106–111. AAAI, Boston (1990)

    Google Scholar 

  10. Pinkas, G.: Reasoning, nonmonotonicity and learning in connectionist networks that capture prepositional knowledge. Artificial Intelligence 77, 203–347 (1995)

    Article  MATH  MathSciNet  Google Scholar 

  11. Charniak, E., Shimony, S.E.: Cost-based abduction and MAP explanation. Artificial Intelligence 66, 345–374 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  12. Den, Y.: Generalized Chart Algorithm: An Efficient Procedure for Cost-Based Abduction. In: 32nd annual Meeting of the Association for Computational Linguistics, pp. 218–225. New Mexico Association for Computational Linguistics, Las Cruces (1994)

    Chapter  Google Scholar 

  13. Ishizuka, M., Matsuo, Y.: SL Method for Computing a Nearoptimal Solution Using Linear and Non-Linear Programming in Cost-Based Hypothetical Reasoning. Knowledge-based systems 15, 369–376 (2002)

    Article  Google Scholar 

  14. Santos, E.: A Linear constraint satisfaction approach to Cost-Based Abduction. Artificial Intelligence 65(1), 1–27 (1994)

    Article  MATH  MathSciNet  Google Scholar 

  15. Santos, E.J., Santos, E.S.: Polynomial Solvability of Cost-Based Abduction. Artificial Intelligence 86, 157–170 (1996)

    Article  MathSciNet  Google Scholar 

  16. Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. National Academy of Science 79, 2554–2558 (1982)

    Article  MathSciNet  Google Scholar 

  17. Murphy, K.: A Brief Introduction to Graphical Models and Bayesian Networks, http://www.cs.ubc.ca/~murphyk/Bayes/bnintro.html

Download references

Author information

Authors and Affiliations

  1. Department of Computer Science, University of Toronto, Toronto, ON

    Emad A. M. Andrews & Anthony J. Bonner

Authors
  1. Emad A. M. Andrews
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Anthony J. Bonner
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Department of Electronic Engineering, City University of Hong Kong, Hong Kong,  

    Chi Sing Leung

  2. School of Electrical Engineering and Computer Science, Kyungpook National University, 1370 Sankyuk-Dong, Puk-Gu, 702-701, Taegu, Korea

    Minho Lee

  3. School of Information Technology, King Mongkut’s University of Technology Thonburi, 126 Pracha-U-Thit Rd., Bangmod, Thungkru, 10140, Bangkok, Thailand

    Jonathan H. Chan

Rights and permissions

Reprints and permissions

Copyright information

© 2009 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

Andrews, E.A.M., Bonner, A.J. (2009). Finding MAPs Using High Order Recurrent Networks. In: Leung, C.S., Lee, M., Chan, J.H. (eds) Neural Information Processing. ICONIP 2009. Lecture Notes in Computer Science, vol 5863. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-10677-4_11

Download citation

  • DOI: https://doi.org/10.1007/978-3-642-10677-4_11

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-642-10676-7

  • Online ISBN: 978-3-642-10677-4

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation