THE LIQUID STATE MACHINE IS NOT ROBUST TO PROBLEMS IN ITS COMPONENTS BUT TOPOLOGICAL CONSTRAINTS CAN RESTORE ROBUSTNESS

Hananel Hazan, Larry Manevitz

2010

Abstract

The Liquid State Machine (LSM) is a method of computing with temporal neurons, which can be used amongst other things for classifying intrinsically temporal data directly unlike standard artificial neural networks. It has also been put forward as a natural model of certain kinds of brain functions. There are two results in this paper: (1) We show that the LSM as normally defined cannot serve as a natural model for brain function. This is because they are very vulnerable to failures in parts of the model. This result is in contrast to work by Maass et al which showed that these models are robust to noise in the input data. (2) We show that specifying certain kinds of topological constraints (such as "small world assumption"), which have been claimed are reasonably plausible biologically, can restore robustness in this sense to LSMs.

References

  1. Barabás, A.-L., & Albert, R. (1999). Emergence of Scaling in Random Networks. SCIENCE , 286, 509 - 512.
  2. Barabás, A.-L., & Albert, R. (2000). Topology of evolving networks: local events and universality. 85:5234-7.
  3. Biancon, G., & Barabási, A.-L. (2001). Competition and multiscaling in evolving networks. Europhys Lett , 54:436.
  4. Chklovskii, L. R. (2009, Jul). Structural Properties of the Caenorhabditis elegans Neuronal Network.
  5. Danielle, B. S., & Bullmore, E. (2006). Small-world brain networks. Neuroscientist , 12(6), 512-523.
  6. Fernando, C., & Sojakka, S. (2005). Pattern Recognition in a Bucket. In Advances in Artificial Life (Vol. 2801/2003, pp. 588-597). Springer Berlin / Heidelberg.
  7. Gütig, R., & Sompolinsky, H. (2006). The tempotron: a neuron that learns spike timing-based decision. ature Neuroscience , 9(3), 420-428.
  8. Izhikevich, E. M. (2003). Simple Model of Spiking Neurons. IEEE TRANSACTIONS ON NEURAL NETWORKS , 14 (6), 1569-1572.
  9. Jaeger, H. (2001). "The ëcho state" approach to analysing and training recurrent neural networks. German National Research Institute for Computer Science.
  10. Maass, W. (1999). Paradigms for computing with Spiking Neurons. Springer.
  11. Maass, W., Natschläger, T., & Markram, H. (2002). Realtime computing without stable states: A new framework for neural computation based on perturbations. Neural Computation , 14 (11), 2531- 2560.
  12. Maass, W; Natschläger, T; Markram, H. (2004). Computational models for generic cortical microcircuits. In J. Feng, Computational Neuroscience: A Comprehensive Approach (pp. 575- 605). Boca Raton: Chapman & Hall/CRC.
  13. Manevitz, L. M., & Marom, S. (2002). Modeling the process of rate selection in neuronal activity. Journal of Theoretical Biology , 216(3), 337-343.
  14. McCullough, W. S., & Pitts, W. (1943). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biophysics , 5, 115-127.
  15. Widrow, B., & Hoff, M. (1960). Adaptive Switching Circuits. IRE WESCON Convention Record , 4, 96- 104.
Download


Paper Citation


in Harvard Style

Hazan H. and Manevitz L. (2010). THE LIQUID STATE MACHINE IS NOT ROBUST TO PROBLEMS IN ITS COMPONENTS BUT TOPOLOGICAL CONSTRAINTS CAN RESTORE ROBUSTNESS . In Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010) ISBN 978-989-8425-32-4, pages 258-264. DOI: 10.5220/0003058902580264


in Bibtex Style

@conference{icnc10,
author={Hananel Hazan and Larry Manevitz},
title={THE LIQUID STATE MACHINE IS NOT ROBUST TO PROBLEMS IN ITS COMPONENTS BUT TOPOLOGICAL CONSTRAINTS CAN RESTORE ROBUSTNESS},
booktitle={Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)},
year={2010},
pages={258-264},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003058902580264},
isbn={978-989-8425-32-4},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Conference on Fuzzy Computation and 2nd International Conference on Neural Computation - Volume 1: ICNC, (IJCCI 2010)
TI - THE LIQUID STATE MACHINE IS NOT ROBUST TO PROBLEMS IN ITS COMPONENTS BUT TOPOLOGICAL CONSTRAINTS CAN RESTORE ROBUSTNESS
SN - 978-989-8425-32-4
AU - Hazan H.
AU - Manevitz L.
PY - 2010
SP - 258
EP - 264
DO - 10.5220/0003058902580264