Interactive Evolving Recurrent Neural Networks Are Super-turing

Understanding the dynamical and computational capabilities of neural models represents an issue of central importance. In this context, recent results show that interactive evolving recurrent neural networks are super-Turing, irrespective of whether their synaptic weights are rational or real. We extend these results by showing that interactive evolving recurrent neural networks are not only super-Turing, but also capable of simulating any other possible interactive deterministic system. In this sense, interactive evolving recurrent neural networks represents a super-Turing universal model of computation, irrespective of whether their synaptic weights are rational or real.

[1]  Peter Wegner,et al.  Interactive , 2021, Encyclopedia of the UN Sustainable Development Goals.

[2]  Peter Wegner,et al.  Principles of Interactive Computation , 2006 .

[3]  Alessandro E. P. Villa,et al.  The expressive power of analog recurrent neural networks on infinite input streams , 2012, Theor. Comput. Sci..

[4]  Marvin Minsky,et al.  Computation : finite and infinite machines , 2016 .

[5]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[6]  Jan van Leeuwen,et al.  Beyond the Turing Limit: Evolving Interactive Systems , 2001, SOFSEM.

[7]  Alessandro E. P. Villa,et al.  The Super-Turing Computational Power of Interactive Evolving Recurrent Neural Networks , 2013, ICANN.

[8]  Hava T. Siegelmann,et al.  On the Computational Power of Neural Nets , 1995, J. Comput. Syst. Sci..

[9]  W S McCulloch,et al.  A logical calculus of the ideas immanent in nervous activity , 1990, The Philosophy of Artificial Intelligence.

[10]  Scott A. Smolka,et al.  Interactive Computation: The New Paradigm , 2006 .

[11]  Pekka Orponen,et al.  General-Purpose Computation with Neural Networks: A Survey of Complexity Theoretic Results , 2003, Neural Computation.

[12]  Hava T. Siegelmann,et al.  Neural networks and analog computation - beyond the Turing limit , 1999, Progress in theoretical computer science.

[13]  Günther Palm,et al.  Artificial Neural Networks and Machine Learning – ICANN 2013 , 2013, Lecture Notes in Computer Science.

[14]  Leszek Pacholski,et al.  SOFSEM 2001: Theory and Practice of Informatics , 2001, Lecture Notes in Computer Science.

[15]  Jan van Leeuwen,et al.  The Turing machine paradigm in contemporary computing , 2001 .

[16]  John Longley.  Interpreting Localized Computational Effects Using Operators of Higher Type , 2008, CiE.

[17]  A. Turing.  On Computable Numbers, with an Application to the Entscheidungsproblem. , 1937 .

[18]  B. Engquist,et al.  Mathematics Unlimited: 2001 and Beyond , 2001 .

[19]  Jan van Leeuwen,et al.  How We Think of Computing Today , 2008, CiE.

[20]  Hava T. Siegelmann,et al.  Evolving recurrent neural networks are super-Turing , 2011, The 2011 International Joint Conference on Neural Networks.

[21]  John von Neumann,et al.  The Computer and the Brain , 1960 .

[22]  Hava T. Siegelmann,et al.  Analog computation via neural networks , 1993, [1993] The 2nd Israel Symposium on Theory and Computing Systems.

[23]  Jan van Leeuwen,et al.  A Theory of Interactive Computation , 2006 .

[24]  Hava T. Siegelmann,et al.  The Computational Power of Interactive Recurrent Neural Networks , 2012, Neural Computation.

[25]  S C Kleene,et al.  Representation of Events in Nerve Nets and Finite Automata , 1951 .