Abstract
The ARNN abstract computer, extensively analysed in [28], introduces an analogue-digital model of computation in discrete time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Analogue Recurrent Neural Net.
- 2.
Real weights are quite common in the neural net literature.
- 3.
A few rational weights being enough for the purpose.
- 4.
In fact, the truncated reals. The amount of precision depends on the size of the input.
- 5.
This is still conjecture.
- 6.
ARNN computes with a two-sided experiment.
- 7.
A time constructible function.
References
Ambaram, T., Beggs, E., Costa, J.F., Poças, D., Tucker, J.V.: An analogue-digital model of computation: turing machines with physical oracles. In: Adamatzky, A. (ed.) Advances in Unconventional Computing. ECC, vol. 22, pp. 73–115. Springer, Cham (2017). doi:10.1007/978-3-319-33924-5_4
Beggs, E., Cortez, P., Costa, J.F., Tucker, J.V.: A hierarchy for \( BPP //\log \!\star \) based on counting calls to an oracle. In: Adamatzky, A. (ed.) Emergent Computation. ECC, vol. 24, pp. 39–56. Springer, Cham (2017). doi:10.1007/978-3-319-46376-6_3
Beggs, E., Cortez, P., Costa, J.F., Tucker, J.V.: Classifying the computational power of stochastic physical oracles (2017, submitted)
Beggs, E., Costa, J.F., Poças, D., Tucker, J.V.: Oracles that measure thresholds: the Turing machine and the broken balance. J. Log. Comput. 23(6), 1155–1181 (2013)
Beggs, E., Costa, J.F., Loff, B., Tucker, J.V.: Computational complexity with experiments as oracles. Proc. Roy. Soc. Ser. A (Math. Phys. Eng. Sci.) 464(2098), 2777–2801 (2008)
Beggs, E., Costa, J.F., Loff, B., Tucker, J.V.: Computational complexity with experiments as oracles II. Upper bounds. Proc. Roy. Soc. Ser. A (Math. Phys. Eng. Sci.) 465(2105), 1453–1465 (2009)
Beggs, E., Costa, J.F., Poças, D., Tucker, J.V.: A natural computation model of positive relativisation. Int. J. Unconv. Comput. 10(1–2), 111–141 (2013)
Beggs, E., Costa, J.F., Poças, D., Tucker, J.V.: Computations with oracles that measure vanishing quantities. Math. Struct. Comput. Sci. (2017, to appear)
Beggs, E., Costa, J.F., Poças, D., Tucker, J.V.: An analogue-digital church-turing thesis. Int. J. Found. Comput. Sci. 25(4), 373–389 (2014)
Beggs, E., Costa, J.F., Tucker, J.V.: Computational models of measurement and Hempel’s axiomatization. In: Carsetti, A. (ed.) Causality, Meaningful Complexity and Embodied Cognition. (TDLA), vol. 46, pp. 155–184. Springer, Dordrecht (2010). doi:10.1007/978-90-481-3529-5_9
Beggs, E., Costa, J.F., Tucker, J.V.: Limits to measurement in experiments governed by algorithms. Math. Struct. Comput. Sci. 20(06), 1019–1050 (2010)
Beggs, E., Costa, J.F., Tucker, J.V.: Physical oracles: the Turing machine and the Wheatstone bridge. Stud. Logica. 95(1–2), 279–300 (2010)
Beggs, E., Costa, J.F., Tucker, J.V.: Axiomatising physical experiments as oracles to algorithms. Philos. Trans. Roy. Soc. Ser. A (Math. Phys. Eng. Sci.) 370(12), 3359–3384 (2012)
Beggs, E., Costa, J.F., Tucker, J.V.: The impact of models of a physical oracle on computational power. Math. Struct. Comput. Sci. 22(5), 853–879 (2012)
Beggs, E., Costa, J.F., Tucker, J.V.: Three forms of physical measurement and their computability. Rev. Symb. Log. 7(4), 618–646 (2014)
Bekey, G.A., Karplus, W.J.: Hybrid Computation. Wiley, Hoboken (1968)
Bournez, O., Cosnard, M.: On the computational power of dynamical systems and hybrid systems. Theoret. Comput. Sci. 168(2), 417–459 (1996)
Carnap, R.: Philosophical Foundations of Physics. Basic Books, New York City (1966)
Costa, J.F., Leong, R.: The ARNN model relativizes P == NP and P =/= NP. Theoret. Comput. Sci. 499(1), 2–22 (2013)
Davis, M.: The myth of hypercomputation. In: Teuscher, C. (ed.) Alan Turing: The Life and Legacy of a Great Thinker, pp. 195–212. Springer, Heidelberg (2006). doi:10.1007/978-3-662-05642-4_8
Davis, M.: Why there is no such discipline as hypercomputation. Appl. Math. Comput. 178(1), 4–7 (2006)
Geroch, R., Hartle, J.B.: Computability and physical theories. Found. Phys. 16(6), 533–550 (1986)
Hempel, C.G.: Fundamentals of concept formation in empirical science. Int. Encycl. Unified Sci. 2(7) (1952)
Kelly, K.T.: The Logic of Reliable Inquiry. Oxford University Press, Oxford (1996)
Kilian, J., Siegelmann, H.T.: The dynamic universality of sigmoidal neural networks. Inf. Comput. 128(1), 48–56 (1996)
Krantz, D.H., Duncan Luce, R., Suppes, P., Tversky, A.: Foundations of Measurement, vol. I. Dover, Mineola (2007)
Moore, C.: Unpredictability and undecidability in dynamical systems. Phys. Rev. Lett. 64(20), 2354–2357 (1990)
Siegelmann, H.T.: Neural Networks and Analog Computation: Beyond the Turing Limit. Birkhäuser, Basel (1999)
Woods, D., Naughton, T.J.: An optical model of computation. Theoret. Comput. Sci. 334(2005), 227–258 (2004)
Younger, A.S., Redd, E., Siegelmann, H.: Development of physical super-turing analog hardware. In: Ibarra, O.H., Kari, L., Kopecki, S. (eds.) UCNC 2014. LNCS, vol. 8553, pp. 379–391. Springer, Cham (2014). doi:10.1007/978-3-319-08123-6_31
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Costa, J.F. (2017). The Power of Analogue-Digital Machines. In: Patitz, M., Stannett, M. (eds) Unconventional Computation and Natural Computation. UCNC 2017. Lecture Notes in Computer Science(), vol 10240. Springer, Cham. https://doi.org/10.1007/978-3-319-58187-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-319-58187-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-58186-6
Online ISBN: 978-3-319-58187-3
eBook Packages: Computer ScienceComputer Science (R0)