On the Computational Power of Asynchronous Axon Membrane Systems

Axon membrane systems, also called axon P systems, are a group of neuron system inspired neural computing devices. The system are designed by the mimic of the way axon (connecting neurons in central nerves systems) processing impulse signals passing along it. In the systems, all the “computing units” are aligned one after another along the axon, achieving a linear topological structure. It was known that synchronous axon P systems can compute the families of Turing computable sets of both natural numbers and recursive functions. However, the computational power of asynchronous axon P systems is still open. In this paper, we investigate the computational power of asynchronous axon P systems, where the nonsynchronization is induced by either the node's asynchronously spiking (working in asynchronous mode) or the randomly assigned time consumption for each time spiking of the nodes (working in time-free mode). As results, it is proved that axon P systems working in either asynchronous or time-free mode are Turing universal as number generators, which indicates that the nonsynchronization will not reduce the computation power of axon P systems. It is worth noting that it needs <inline-formula><tex-math notation="LaTeX">$O(n)$</tex-math></inline-formula> spikes to encode natural number <inline-formula><tex-math notation="LaTeX">$n$</tex-math></inline-formula> in asynchronous axon P systems, but it needs <inline-formula><tex-math notation="LaTeX">$O(n^2)$</tex-math></inline-formula> spikes in Turing universal synchronous axon P systems. These results partially answer an open problem left in [IEEE NNLS 26(11): 2816-29, 2015], and may also provide some hints on designing novel learning strategies by imposing computation tasks on the synapses of neural networks models.

[1]  J. Knott.  The organization of behavior: A neuropsychological theory , 1951 .

[2]  Ye Tian,et al.  An Indicator-Based Multiobjective Evolutionary Algorithm With Reference Point Adaptation for Better Versatility , 2018, IEEE Transactions on Evolutionary Computation.

[3]  Xiangxiang Zeng,et al.  Performing Four Basic Arithmetic Operations With Spiking Neural P Systems , 2012, IEEE Transactions on NanoBioscience.

[4]  Ye Tian,et al.  A Decision Variable Clustering-Based Evolutionary Algorithm for Large-Scale Many-Objective Optimization , 2018, IEEE Transactions on Evolutionary Computation.

[5]  Pan Zheng,et al.  Spiking Neural P Systems With Learning Functions , 2019, IEEE Transactions on NanoBioscience.

[6]  Nikola K. Kasabov,et al.  NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data , 2014, Neural Networks.

[7]  Anders Krogh,et al.  Neural Network Ensembles, Cross Validation, and Active Learning , 1994, NIPS.

[8]  Dean V. Buonomano,et al.  A Neural Network Model of Temporal Code Generation and Position-Invariant Pattern Recognition , 1999, Neural Computation.

[9]  G. Buzsáki,et al.  NeuroGrid: recording action potentials from the surface of the brain , 2014, Nature Neuroscience.

[10]  Christian W. Eurich,et al.  Multidimensional Encoding Strategy of Spiking Neurons , 2000, Neural Computation.

[11]  Xun Wang,et al.  Homogenous spiking neural P systems with anti-spikes , 2013, Neural Computing and Applications.

[12]  Ethan M. Goldberg,et al.  Electrogenic Tuning of the Axon Initial Segment , 2009, The Neuroscientist : a review journal bringing neurobiology, neurology and psychiatry.

[13]  Ye Tian,et al.  A Strengthened Dominance Relation Considering Convergence and Diversity for Evolutionary Many-Objective Optimization , 2019, IEEE Transactions on Evolutionary Computation.

[14]  Linqiang Pan,et al.  Asynchronous spiking neural P systems with local synchronization , 2013, Inf. Sci..

[15]  Linqiang Pan,et al.  On the Universality and Non-Universality of Spiking Neural P Systems With Rules on Synapses , 2015, IEEE Transactions on NanoBioscience.

[16]  Oscar H. Ibarra,et al.  Asynchronous spiking neural P systems , 2009, Theor. Comput. Sci..

[17]  G Deco,et al.  The coding of information by spiking neurons: an analytical study. , 1998, Network.

[18]  Chen Hai-ming,et al.  Computing along the axon , 2006 .

[19]  Alfonso Rodríguez-Patón,et al.  A Parallel Bioinspired Framework for Numerical Calculations Using Enzymatic P System With an Enzymatic Environment , 2018, IEEE Access.

[20]  Linqiang Pan,et al.  Spiking neural P systems with request rules , 2016, Neurocomputing.

[21]  Giancarlo Mauri,et al.  Uniform solutions to SAT and Subset Sum by spiking neural P systems , 2008, Natural Computing.

[22]  Eitan M. Gurari,et al.  Introduction to the theory of computation , 1989 .

[23]  Steve Renals,et al.  Convolutional Neural Networks for Distant Speech Recognition , 2014, IEEE Signal Processing Letters.

[24]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[25]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[26]  Xiangxiang Zeng,et al.  A Network Reduction-Based Multiobjective Evolutionary Algorithm for Community Detection in Large-Scale Complex Networks , 2020, IEEE Transactions on Cybernetics.

[27]  Linqiang Pan,et al.  Normal Forms for Some Classes of Sequential Spiking Neural P Systems , 2013, IEEE Transactions on NanoBioscience.

[28]  Linqiang Pan,et al.  Time-free solution to SAT problem using P systems with active membranes , 2014, Theor. Comput. Sci..

[29]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[30]  Andrei Paun,et al.  On the Universality of Axon P Systems , 2015, IEEE Transactions on Neural Networks and Learning Systems.

[31]  Jun Wang,et al.  A Note on the Generative Power of Axon P Systems , 2009, Int. J. Comput. Commun. Control.

[32]  Ruslan Mitkov,et al.  The Oxford handbook of computational linguistics , 2003 .

[33]  Oscar H. Ibarra,et al.  On spiking neural P systems , 2006, Natural Computing.

[34]  D. O. Hebb,et al.  The organization of behavior , 1988 .

[35]  Xiangxiang Zeng,et al.  Homogeneous Spiking Neural P Systems , 2009, Fundam. Informaticae.

[36]  Pan Zheng,et al.  On the Computational Power of Spiking Neural P Systems with Self-Organization , 2016, Scientific Reports.

[37]  Sander M. Bohte,et al.  Error-backpropagation in temporally encoded networks of spiking neurons , 2000, Neurocomputing.

[38]  Gheorghe Paun,et al.  Computing with Membranes , 2000, J. Comput. Syst. Sci..

[39]  Xiangxiang Zeng,et al.  A Parallel Workflow Pattern Modeling Using Spiking Neural P Systems With Colored Spikes , 2018, IEEE Transactions on NanoBioscience.

[40]  J.A. Anderson,et al.  Neural Network Models for Pattern Recognition and Associative Memory , 2002 .

[41]  Gheorghe Paun,et al.  The Oxford Handbook of Membrane Computing , 2010 .

[42]  Xiangxiang Zeng,et al.  Time-Free Spiking Neural P Systems , 2011, Neural Computation.

[43]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[44]  Ursula Dresdner,et al.  Computation Finite And Infinite Machines , 2016 .

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

[46]  Fabio L. Traversa,et al.  Universal Memcomputing Machines , 2014, IEEE Transactions on Neural Networks and Learning Systems.

[47]  Alfonso Rodríguez-Patón,et al.  A Parallel Image Skeletonizing Method Using Spiking Neural P Systems with Weights , 2018, Neural Processing Letters.

[48]  Xun Wang,et al.  Design of logic gates using spiking neural P systems with homogeneous neurons and astrocytes-like control , 2016, Inf. Sci..

[49]  Andrei Paun,et al.  Small universal spiking neural P systems , 2007, Biosyst..

[50]  Andrzej J. Kasinski,et al.  Supervised Learning in Spiking Neural Networks with ReSuMe: Sequence Learning, Classification, and Spike Shifting , 2010, Neural Computation.