Abstract
In the effort to refine the analysis of computational power of neural nets between integer and rational weights we study a hybrid binary-state network with an extra analog unit. We introduce a finite automaton with a register which is shown to be computationally equivalent to such a network. The main result is a sufficient condition for a language accepted by this automaton to be regular which is based on the new concept of a quasi-periodic power series. These preliminary results suggest an interesting connection with the active research field on the expansions of numbers in non-integer bases which seems to be a fruitful area for further research including many important open problems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Adamczewski, B., Frougny, C., Siegel, A., Steiner, W.: Rational numbers with purely periodic β-expansion. Bulletin of The London Mathematical Society 42(3), 538–552 (2010)
Allouche, J.P., Clarke, M., Sidorov, N.: Periodic unique beta-expansions: The Sharkovskiĭ ordering. Ergodic Theory and Dynamical Systems 29(4), 1055–1074 (2009)
Alon, N., Dewdney, A.K., Ott, T.J.: Efficient simulation of finite automata by neural nets. Journal of the ACM 38(2), 495–514 (1991)
Balcázar, J.L., Gavaldà, R., Siegelmann, H.T.: Computational power of neural networks: A characterization in terms of Kolmogorov complexity. IEEE Transactions on Information Theory 43(4), 1175–1183 (1997)
Chunarom, D., Laohakosol, V.: Expansions of real numbers in non-integer bases. Journal of the Korean Mathematical Society 47(4), 861–877 (2010)
Dassow, J., Mitrana, V.: Finite automata over free groups. International Journal of Algebra and Computation 10(6), 725–738 (2000)
Glendinning, P., Sidorov, N.: Unique representations of real numbers in non-integer bases. Mathematical Research Letters 8(4), 535–543 (2001)
Hare, K.G.: Beta-expansions of Pisot and Salem numbers. In: Proceedings of the Waterloo Workshop in Computer Algebra 2006: Latest Advances in Symbolic Algorithms, pp. 67–84. World Scientific (2007)
Horne, B.G., Hush, D.R.: Bounds on the complexity of recurrent neural network implementations of finite state machines. Neural Networks 9(2), 243–252 (1996)
Ibarra, O.H., Sahni, S., Kim, C.E.: Finite automata with multiplication. Theoretical Computer Science 2(3), 271–294 (1976)
Indyk, P.: Optimal simulation of automata by neural nets. In: Mayr, E.W., Puech, C. (eds.) STACS 1995. LNCS, vol. 900, pp. 337–348. Springer, Heidelberg (1995)
Kambites, M.E.: Formal languages and groups as memory. Communications in Algebra 37(1), 193–208 (2009)
Kilian, J., Siegelmann, H.T.: The dynamic universality of sigmoidal neural networks. Information and Computation 128(1), 48–56 (1996)
Koiran, P.: A family of universal recurrent networks. Theoretical Computer Science 168(2), 473–480 (1996)
Komornik, V., Loreti, P.: Subexpansions, superexpansions and uniqueness properties in non-integer bases. Periodica Mathematica Hungarica 44(2), 197–218 (2002)
Minsky, M.: Computations: Finite and Infinite Machines. Prentice-Hall, Englewood Cliffs (1967)
Mitrana, V., Stiebe, R.: Extended finite automata over groups. Discrete Applied Mathematics 108(3), 287–300 (2001)
Orponen, P.: Computing with truly asynchronous threshold logic networks. Theoretical Computer Science 174(1-2), 123–136 (1997)
Parry, W.: On the β-expansions of real numbers. Acta Mathematica Hungarica 11(3), 401–416 (1960)
Rényi, A.: Representations for real numbers and their ergodic properties. Acta Mathematica Academiae Scientiarum Hungaricae 8(3-4), 477–493 (1957)
Salehi, Ö., Yakaryılmaz, A., Say, A.C.C.: Real-time vector automata. In: Gąsieniec, L., Wolter, F. (eds.) FCT 2013. LNCS, vol. 8070, pp. 293–304. Springer, Heidelberg (2013)
Schmidt, K.: On periodic expansions of Pisot numbers and Salem numbers. Bulletin of the London Mathematical Society 12(4), 269–278 (1980)
Sidorov, N.: Expansions in non-integer bases: Lower, middle and top orders. Journal of Number Theory 129(4), 741–754 (2009)
Siegelmann, H.T.: Recurrent neural networks and finite automata. Journal of Computational Intelligence 12(4), 567–574 (1996)
Siegelmann, H.T.: Neural Networks and Analog Computation: Beyond the Turing Limit. Birkhäuser, Boston (1999)
Siegelmann, H.T., Sontag, E.D.: Analog computation via neural networks. Theoretical Computer Science 131(2), 331–360 (1994)
Siegelmann, H.T., Sontag, E.D.: On the computational power of neural nets. Journal of Computer System Science 50(1), 132–150 (1995)
Šíma, J.: Analog stable simulation of discrete neural networks. Neural Network World 7(6), 679–686 (1997)
Šíma, J.: Energy complexity of recurrent neural networks. Neural Computation 26(5), 953–973 (2014)
Šíma, J., Orponen, P.: General-purpose computation with neural networks: A survey of complexity theoretic results. Neural Computation 15(12), 2727–2778 (2003)
Šíma, J., Wiedermann, J.: Theory of neuromata. Journal of the ACM 45(1), 155–178 (1998)
Šorel, M., Šíma, J.: Robust RBF finite automata. Neurocomputing 62, 93–110 (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Šíma, J. (2014). The Power of Extra Analog Neuron. In: Dediu, AH., Lozano, M., Martín-Vide, C. (eds) Theory and Practice of Natural Computing. TPNC 2014. Lecture Notes in Computer Science, vol 8890. Springer, Cham. https://doi.org/10.1007/978-3-319-13749-0_21
Download citation
DOI: https://doi.org/10.1007/978-3-319-13749-0_21
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-13748-3
Online ISBN: 978-3-319-13749-0
eBook Packages: Computer ScienceComputer Science (R0)