Turing Machines Are Recurrent Neural Networks

@inproceedings{Hyotyniemi1996TuringMA,
  title={Turing Machines Are Recurrent Neural Networks},
  author={Heikki Hyotyniemi},
  year={1996}
}
Any algebraically computable function can be expressed as a recurrent neural network structure consisting of identical computing elements (or, equivalently, as a nonlinear discrete-time system of the form x(k + 1) = f(Ax(k)), where f() is a simplècut' function). A constructive proof is presented in this paper. 
Highly Cited
This paper has 29 citations. REVIEW CITATIONS
21 Citations
6 References
Similar Papers

Citations

Publications citing this paper.

References

Publications referenced by this paper.
Showing 1-6 of 6 references

Genes, Codes, and Dynamic Systems

  • H. Hyotyniemi, H. Koivo
  • Proceedings of the Second Nordic Workshop on…
  • 1996

Correlations|Building Blocks of Intelligence

  • H. Hy otyniemi
  • Finnish Arti cial Intelligence Society,
  • 1995
2 Excerpts

Petri Net Theory and the Modeling of Systems

  • J. L. Peterson
  • 1981

Similar Papers

Loading similar papers…