Guiding Probabilistic Logical Inference with Nonlinear Dynamical Attention Allocation

  • Cosmo Harrigan
  • Ben Goertzel
  • Matthew Iklé
  • Amen Belayneh
  • Gino Yu
Conference paper

DOI: 10.1007/978-3-319-09274-4_24

Part of the Lecture Notes in Computer Science book series (LNCS, volume 8598)
Cite this paper as:
Harrigan C., Goertzel B., Iklé M., Belayneh A., Yu G. (2014) Guiding Probabilistic Logical Inference with Nonlinear Dynamical Attention Allocation. In: Goertzel B., Orseau L., Snaider J. (eds) Artificial General Intelligence. AGI 2014. Lecture Notes in Computer Science, vol 8598. Springer, Cham

Abstract

In order to explore the practical manifestations of the “cognitive synergy” between the PLN (Probabilistic Logic Networks) and ECAN (Economic Attention Network) components of the OpenCog AGI architecture, we explore the behavior of PLN and ECAN operating together on two standard test problems commonly used with Markov Logic Networks (MLN). Our preliminary results suggest that, while PLN can address these problems adequately, ECAN offers little added value for the problems in their standard form. However, we outline modified versions of the problem that we hypothesize would demonstrate the value of ECAN more effectively, via inclusion of confounding information that needs to be heuristically sifted through.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Cosmo Harrigan
    • 1
    • 2
    • 6
  • Ben Goertzel
    • 2
  • Matthew Iklé
    • 3
  • Amen Belayneh
    • 4
    • 5
  • Gino Yu
    • 5
  1. 1.OpenCog FoundationHong Kong
  2. 2.Novamente LLCUSA
  3. 3.Adams State UniversityUSA
  4. 4.iCog LabsHong Kong
  5. 5.School of DesignHong Kong Poly UHong Kong
  6. 6.University of WashingtonUSA

Personalised recommendations