Pattern Recognition in a Bucket

  • Chrisantha Fernando
  • Sampsa Sojakka
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2801)

Abstract

This paper demonstrates that the waves produced on the surface of water can be used as the medium for a “Liquid State Machine” that pre-processes inputs so allowing a simple perceptron to solve the XOR problem and undertake speech recognition. Interference between waves allows non-linear parallel computation upon simultaneous sensory inputs. Temporal patterns of stimulation are converted to spatial patterns of water waves upon which a linear discrimination can be made. Whereas Wolfgang Maass’ Liquid State Machine requires fine tuning of the spiking neural network parameters, water has inherent self-organising properties such as strong local interactions, time-dependent spread of activation to distant areas, inherent stability to a wide variety of inputs, and high complexity. Water achieves this “for free”, and does so without the time-consuming computation required by realistic neural models. An analogy is made between water molecules and neurons in a recurrent neural network.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Maass, W., Natschlager, T., et al.: Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations. Neural Computation 14, 2531–2560 (2002)MATHCrossRefGoogle Scholar
  2. 2.
    Hopfield, J.J., Brody, C.D.: What is a moment? ”Cortical” sensory integration over a brief interval. PNAS 97(25), 13919–13924 (2000)CrossRefGoogle Scholar
  3. 3.
    Auer, P., Burgsteiner, H., et al.: The p-Delta Learning Rule for Parallel Perceptrons (2002) (submitted for publication), http://www.cis.tugraz.at/igi/pauer/publications.html
  4. 4.
    Adamatzky, A.: Computing in nonlinear media: make waves, study collisions. In: Kelemen, J., Sosík, P. (eds.) ECAL 2001. LNCS (LNAI), vol. 2159, pp. 1–11. Springer, Heidelberg (2001)CrossRefGoogle Scholar
  5. 5.
    Adamatzky, A., De Lacy Costello, B.P.J.: Experimental logical gates in a reaction-difusion medium: The XOR gate and beyond. Physical Review E 66, 46112 (2002)CrossRefGoogle Scholar
  6. 6.
    Goldenholz, D.: Liquid Computing: A Real Effect. BE707 Final Project. Boston University School of Medicine, Boston (2002), http://www.lsm.tugraz.at/people.html Google Scholar
  7. 7.
    MacLennan, B.: Field Computation in Natural and Artificial Intelligence. Knoxville, University of Tennessee. Report UT-CS-99-422. (1999), http://www.cs.utk.edu/mclennan/fieldcomp.html
  8. 8.
    McCulloch, W.S., Pitts, W.: A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathamatical Biophysics 5, 115–133 (1943)MATHCrossRefMathSciNetGoogle Scholar
  9. 9.
    Freeman, W.: Mesoscopic Neurodynamics: From neuron to brain. Journal of Physiology (Paris) 94, 303–322 (2000)CrossRefGoogle Scholar
  10. 10.
    Walmsley, I.: Computing with interference: All-optical single-query 50- element database search. In: Conference on Lasers and Electro-Optics/Quantum Electronics and Laser Science, Baltimore, Maryland (2001)Google Scholar
  11. 11.
    Tononi, E., Sporns, O.: Complexity and Coherency: integrating information in the brain. Trends in Cognitive Sciences 2(12), 474–483 (1998)CrossRefGoogle Scholar
  12. 12.
    Muller, G., Newman, S.: Origination of Organismal Form: Beyond the Gene in Developmental and Evolutionary Biology. MIT Press, Cambridge (2003)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Chrisantha Fernando
    • 1
  • Sampsa Sojakka
    • 1
  1. 1.School of Cognitive and Computer SciencesUniversity of SussexBrightonUK

Personalised recommendations