SSNNS -: a suite of tools to explore spiking neural networks

ABSTRACT

We are interested in engineering smart machines that enable backtracking of emergent behaviors. Our SSNNS simulator consists of hand-picked tools to explore spiking neural networks in more depth with flexibility. SSNNS is based on the Spike Response Model (SRM) with capabilities for short and long term memory. A genetic algorithm, namely CHC, is used independently to generate such example systems that produce patterns of interest. Foundational work in the growing field of spiking neural networks has shown that precise spike timing may be biologically more plausible and computationally powerful than traditional rate-based models[4][7]. We have been using evolution to discover neural configurations that produce patterns of interest.

REFERENCES

• 1: I. Antonov, I. Antonova, E. R. Kandel, and R. D. Hawkins. Activity-dependent presynaptic facilitation and hebbian ltp are both required and interact during classical conditioning in aplysia. Neuron, 37(1):135--47, Jan 2003.
• 2: Sander M. Bohte , Joost N. Kok, Applications of spiking neural networks, Information Processing Letters, v.95 n.6, p.519-520, 30 September 2005 [doi>10.1016/j.ipl.2005.05.018]
• 3: L. J. Eshelman. The CHC Adaptive Search Algorithm: How to Have Safe Search When Engaging in Nontraditional Genetic Recombination. Foundations Of Genetic Algorithms, pages 265-283, 1990.
• 4: Wulfram Gerstner , Werner Kistler, Spiking Neuron Models: An Introduction, Cambridge University Press, New York, NY, 2002
• 5: D. O. Hebb. Organization of behavior. New York: Wiley, 1949.
• 6: D. Z. Jin. Spiking neural network for recognizing spatiotemporal sequences of spikes. Physical Review E,69, 2004.
• 7: Wolfgang Maass , Christopher M. Bishop, Pulsed Neural Networks, MIT Press, Cambridge, MA, 2001
• 8: Wolfgang Maass , Henry Markram, Synapses as dynamic memory buffers, Neural Networks, v.15 n.2, p.155-161, March 2002 [doi>10.1016/S0893-6080(01)00144-7]
• 9: H. Markram, Y. Wang, and M. Tsodyks. Differential signaling via the same axon of neocortical pyramidal neurons. Neurobiology, 95:5323--5328, April 1998.
• 10: D. E. Rumelhart , G. E. Hinton , R. J. Williams, Learning internal representations by error propagation, Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations, MIT Press, Cambridge, MA, 1986
• 11: J. D. Schaffer, L. D. Whitley, and L. J. Eshelman. Combinations of genetic algorithms and neural networks: A survey of the state of the art. In Combinations of Genetic Algorithms and NeuralNetworks, 1992., COGANN-92. International Workshop on, pages 1--37, Philips Labs., Briarcliff Manor, NY, 6 Jun 1992.
• 12: S. Song, K. D. Miller, and L. F. Abbott. Competitive hebbian learning through spike-timing-dependent synaptic plasticity. Nature Neuroscience, 3(9):919--926, 2000.
• 13: L. Watts. Event-driven simulation of networks of spiking neurons. Advances in Neural Information Processing Systems, 6:927--934, 1994.

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Experimental design

Additional Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Time series analysis

  I. Computing Methodologies
  I.6 SIMULATION AND MODELING
      I.6.4 Model Validation and Analysis

General Terms:
Algorithms, Design, Experimentation, Theory, Verification

Keywords:
complexity, genetic algorithms, learning, machine learning, spiking neural networks, temporal pattern recognition