Patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks.

We consider feed-forward and auto-regulation feed-forward neural (weighted) coupled cell networks. In feed-forward neural networks, cells are arranged in layers such that the cells of the first layer have empty input set and cells of each other layer receive only inputs from cells of the previous layer. An auto-regulation feed-forward neural coupled cell network is a feed-forward neural network where additionally some cells of the first layer have auto-regulation, that is, they have a self-loop. Given a network structure, a robust pattern of synchrony is a space defined in terms of equalities of cell coordinates that is flow-invariant for any coupled cell system (with additive input structure) associated with the network. In this paper, we describe the robust patterns of synchrony for feed-forward and auto-regulation feed-forward neural networks. Regarding feed-forward neural networks, we show that only cells in the same layer can synchronize. On the other hand, in the presence of auto-regulation, we prove that cells in different layers can synchronize in a robust way and we give a characterization of the possible patterns of synchrony that can occur for auto-regulation feed-forward neural networks.

[1]  Ian Stewart,et al.  Patterns of Synchrony in Coupled Cell Networks with Multiple Arrows , 2005, SIAM J. Appl. Dyn. Syst..

[2]  Krzysztof Pancerz,et al.  Recurrent Neural Networks in Computer-Based Clinical Decision Support for Laryngopathies: An Experimental Study , 2011, Comput. Intell. Neurosci..

[3]  Bob W. Rink,et al.  Graph fibrations and symmetries of network dynamics , 2014, 1410.6021.

[4]  Ad Aertsen,et al.  Stable propagation of synchronous spiking in cortical neural networks , 1999, Nature.

[5]  Freddie Åström,et al.  A parallel neural network approach to prediction of Parkinson's Disease , 2011, Expert Syst. Appl..

[6]  Markus Diesmann,et al.  The mechanism of synchronization in feed-forward neuronal networks , 2008 .

[7]  Tirtharaj Dash,et al.  Controlling Wall Following Robot Navigation Based on Gravitational Search and Feed Forward Neural Network , 2015, PerMIn '15.

[8]  Sven Jahnke,et al.  Propagating synchrony in feed-forward networks , 2013, Front. Comput. Neurosci..

[9]  M. J. Field,et al.  Heteroclinic Networks in Homogeneous and Heterogeneous Identical Cell Systems , 2015, Journal of Nonlinear Science.

[10]  R Huerta,et al.  Explaining synchrony in feed-forward networks: are McCulloch-Pitts neurons good enough? , 2003, Biological cybernetics.

[11]  M. Golubitsky,et al.  Bifurcations from regular quotient networks: A first insight , 2009 .

[12]  Marcus Pivato,et al.  Symmetry Groupoids and Patterns of Synchrony in Coupled Cell Networks , 2003, SIAM J. Appl. Dyn. Syst..

[13]  A. Reyes.  Experimental and Theoretical Analyses of Synchrony in Feedforward Networks , 2008 .

[14]  Marc Timme,et al.  Computation by switching in complex networks of states. , 2012, Physical review letters.

[15]  H. Markram,et al.  t Synchrony Generation in Recurrent Networks with Frequency-Dependent Synapses , 2000, The Journal of Neuroscience.

[16]  Zachary Chase Lipton.  A Critical Review of Recurrent Neural Networks for Sequence Learning , 2015, ArXiv.

[17]  Gábor Orosz,et al.  Dynamics on Networks of Cluster States for Globally Coupled Phase Oscillators , 2007, SIAM J. Appl. Dyn. Syst..

[18]  Is Synchrony a reasonable coding strategy for visual areas beyond V1 in primates , 2010 .

[19]  Ian Stewart,et al.  Some Curious Phenomena in Coupled Cell Networks , 2004, J. Nonlinear Sci..

[20]  Bob W. Rink,et al.  Amplified Hopf Bifurcations in Feed-Forward Networks , 2013, SIAM J. Appl. Dyn. Syst..

[21]  Martin Golubitsky,et al.  Nilpotent Hopf Bifurcations in Coupled Cell Systems , 2006, SIAM J. Appl. Dyn. Syst..

[22]  Ramón Huerta,et al.  Explaining synchrony in feed-forward networks: , 2003, Biological Cybernetics.

[23]  F. Apollonio,et al.  Effects of pulsed magnetic field on neurons: Cnp signal silences a feed-forward network model , 2013, 2013 6th International IEEE/EMBS Conference on Neural Engineering (NER).

[24]  Manuela A. D. Aguiar,et al.  The Lattice of Synchrony Subspaces of a Coupled Cell Network: Characterization and Computation Algorithm , 2014, J. Nonlinear Sci..

[25]  Idan Segev,et al.  Synchrony is stubborn in feedforward cortical networks , 2003, Nature Neuroscience.

[26]  Mehmet Emin Aydin,et al.  Heuristic-based neural networks for stochastic dynamic lot sizing problem , 2013, Appl. Soft Comput..

[27]  A. Reyes.  Synchrony-dependent propagation of firing rate in iteratively constructed networks in vitro , 2003, Nature Neuroscience.

[28]  Martin Golubitsky,et al.  Feed-forward networks, center manifolds, and forcing , 2012 .

[29]  M. Golubitsky,et al.  The Feed-Forward Chain as a Filter-Amplifier Motif , 2009 .