AUTOMATIC PARALLELIZATION IN NEURAL COMPUTERS

João Pedro Neto

2009

Abstract

Neural Networks are more than just mathematical tools to achieve optimization and learning via sub-symbolic computations. Neural networks can perform several other types of computation, namely symbolic and chaotic computations. The discrete time neural model presented here can perform those three types of computations in a modular way. This paper focuses on how neural networks within this model can be used to automatically parallelize computational processes.

References

  1. Carnell, A., Richardson, D., 2007. Parallel computation in spiking neural nets, Theoretical Computer Science [386]1-2, Elsevier, 57-72.
  2. Gruau, F., Ratajszczak, J., Wibe, J., 1995. A neural compiler, Theoretical Computer Science, 141, 1-52.
  3. Herz, A., Goltisch, T., Machens, C., Jaeger, D., 2006. Modelling Single-Neuron Dynamics & Computations: A Balance of Detail and Abstraction, Science, 314, 80-85.
  4. McCulloch, W., Pitts, W., 1943. A logical calculus of the ideas immanent in nervous activity, Bulletin of Mathematical Biophysics, 5, 115-133.
  5. Neto, J., Siegelmann, H., and Costa, J., 1998. On the Implementation of Programming Languages with Neural Nets, First International Conference on Computing Anticipatory Systems, 1, 201-208.
  6. Neto, J., Costa, J., and Siegelmann, H., 2003. Symbolic Processing in Neural Networks, Journal of Brazilian Computer Society, [8]3, 58-70.
  7. Neto, J. 2006. A Virtual Machine for Neural Computers, 16th International Conference of Artificial Neural Networks, in S. Kollias et al. (eds.), Lecture Notes of Computer Science 4131, Springer-Verlag, 525-534.
  8. Siegelmann, H. and Sontag, E., 1994. Analog Computation via Neural Networks”, Theoretical Computer Science, 131, Elsevier, 331-360.
  9. Siegelmann, H., 1999. Neural Networks and Analog Computation, Beyond the Turing Limit, Birkhäuser.
Download


Paper Citation


in Harvard Style

Neto J. (2009). AUTOMATIC PARALLELIZATION IN NEURAL COMPUTERS . In Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009) ISBN 978-989-674-014-6, pages 397-401. DOI: 10.5220/0002269403970401


in Bibtex Style

@conference{icnc09,
author={João Pedro Neto},
title={AUTOMATIC PARALLELIZATION IN NEURAL COMPUTERS},
booktitle={Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)},
year={2009},
pages={397-401},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0002269403970401},
isbn={978-989-674-014-6},
}


in EndNote Style

TY - CONF
JO - Proceedings of the International Joint Conference on Computational Intelligence - Volume 1: ICNC, (IJCCI 2009)
TI - AUTOMATIC PARALLELIZATION IN NEURAL COMPUTERS
SN - 978-989-674-014-6
AU - Neto J.
PY - 2009
SP - 397
EP - 401
DO - 10.5220/0002269403970401