Nine switch-affine neurons suffice for Turing universality

Neural Networks

Volumn 12, Issue 4-5, 1999, Pages 593-600

  Siegelmann, H T ^a   Margenstern, M ^b  

^a TECHNION ISRAEL INSTITUTE OF TECHNOLOGY   (Israel)

^b UNIVERSITÉ DE LORRAINE   (France)

Author keywords

Recurrent neural networks; Tag systems; Turing machine; Universal computation

Indexed keywords

FINITE AUTOMATA; FUNCTIONS; PIECEWISE LINEAR TECHNIQUES; POLYNOMIALS; RECURRENT NEURAL NETWORKS;

TAG SYSTEMS; UNIVERSAL COMPUTATION;

TURING MACHINES;

ARTICLE; ARTIFICIAL NEURAL NETWORK; COMPUTER SIMULATION; INFORMATION PROCESSING; INFORMATION SCIENCE; LINEAR SYSTEM; MATHEMATICAL COMPUTING; PRIORITY JOURNAL;

EID: 0032807734     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(99)00025-8     Document Type: Article

References (20)

1. Casey M. The dynamics of discrete-time computation with application to recurrent neural networks and finite state machine extraction. Neural Computation. 8:(6):1996;1135-1178.
2. Gavaldà R., Siegelmann H.T. Discontinuities in recurrent neural networks. Neural Computation. 11:(3):1999;715-745.
3. Indyk P. Optimal simulation of automata by neural nets. Mayr E.W., Puech C. Lecture Notes in Computer Science: Proceedings of the Twelfth Annual Symposium on Theoretical Aspects of Computer Science. 1995;337 Springer, Munich.
4. Kilian J., Siegelmann H.T. The dynamic universality of sigmoidal neural networks. Information and Computation. 128:(1):1996;48-56.
5. Koiran P., Cosnard M., Garzon M. Computability with low-dimensional dynamical systems. Theoretical Computer Science. 132:1994;113-128.
6. Maass W., Orponen P. On the effect of analog noise in discrete-time analog computations. Neural Computation. 10:1998;1071-1095.
7. Maass W., Sontag E.D. Analog neural nets with Gaussian or other common noise distributions cannot recognize arbitrary regular languages. Neural Computation. 11:(3):1999;771-782.
8. Margenstern M. Non-erasing Turing machines: a new frontier between a decidable halting problem and universality. Lecture Notes in Computer Science. 911:1995;386-397.
9. Minsky M.L. Computation: Finite and Infinite Machines. 1967;Prentice Hall, Englewood Cliffs, NJ.
10. Moore C. Unpredictability and undecidability in dynamical systems. Physical Review Letters. 64:1990;2354-2357.
11. Pollack, J.B. (1987). On connectionist models of natural language processing. PhD thesis, Computer Science Dept., University of Illinois, Urbana.
12. Post E.L. Absolutely unsolvable problems and relatively undecidable propositions - account of an anticipation. Davis M. The undecidable. 1965;317 Raven Press, New York.
13. Rogozhin Y.V. Sem' universal'nykh mashin Tjuringa. Matematicheskie Issledovanija. 69:1982;76-90. in Russian.
14. Rogozhin Yu.V. Small universal Turing machines. Theoretical Computer Science. 168:(2):1996;215-240.
15. Shannon C.E. A universal Turing machine with two internal states. McCarthy J., Shannon C. Automata Studies. 1956;156 Princeton University, Princeton University Press, NJ.
16. Siegelmann H.T., Sontag E.D. Turing computability with neural nets. Applied Mathematics Letters. 4:(6):1991;77-80.
17. Siegelmann H.T., Sontag E.D. Analog computation via neural networks. Theoretical Computer Science. 131:1994;331-360.
18. Siegelmann H.T., Sontag E.D. On the computational power of neural nets. Journal of Computers and System Science. 50:(1):1995;132-150.
19. Sun, G. Z., Chen, H. H., Lee, Y. C., Giles, C. L. (1991). Turing equivalence of neural networks with second order connection weights, Proceedings of the IEEE INNS International Joint Conference on Neural Networks - Seattle, IEEE Press, Piscataway, NJ, 2 1991357-362.
20. Wang H. Tag systems and lag systems. Mat. Annalen. 152:1963;65-74.