Analog Computation via Neural Networks

  title={Analog Computation via Neural Networks},
  author={Hava T. Siegelmann and Eduardo D. Sontag},
  journal={Theor. Comput. Sci.},
Siegelmann, H.T. and E.D. Sontag, Analog computation via neural networks, Theoretical Computer Science 131 (1994) 331-360. We pursue a particular approach to analog computation, based on dynamical systems of the type used in neural networks research. Our systems have a fixed structure, invariant in time, corresponding to an unchanging number of “neurons”. If allowed exponential time for computation, they turn out to have unbounded power. However, under polynomial-time constraints there are… CONTINUE READING
7 Citations
20 References
Similar Papers


Publications referenced by this paper.
Showing 1-10 of 20 references

On the computational power of neural nets,

  • Siegelmann H.T, E. D. Sontag
  • Proc. Fifth ACM Workshop on Computational…
  • 1992
Highly Influential
4 Excerpts

The Computational and Learning Complexity of Neural Networks, draft

  • I. Parberry
  • 1994
1 Excerpt

Siegelmann, \On the power of sigmoid neural networks,

  • J. Kilian, H.T
  • Proc. Sixth ACM Workshop on Computational…
  • 1993
1 Excerpt

Continuous symbol systems: The logic of connectionism,

  • B. J. MacLennan
  • 1992

An Introduction to Numerical Analysis, Wiley

  • K. E. Atkinson
  • New York,
  • 1989
1 Excerpt

Similar Papers

Loading similar papers…