Exponential H ∞ filtering for switched neural networks with mixed delays

The study focuses on the exponential H ∞ filtering problem of biological neural nets (BNNs). By considering some realistic factors including delays, disturbance and topology changes, the well-known leaky integrate-and-fire model is modified as a switched neural network so that function of a single neuron is identified via the H ∞ filtering instead of biological experimental methods. With the aid of average dwell time method, we provide a delay-dependent sufficient condition, under which the designed filter for the function of every individual neuron in BNNs satisfies H ∞ noise attenuation and exponential stability. Moreover, the design of such a filter is converted into a convex optimisation problem, which can be easily solved by using standard numerical software. Finally, two examples are given to show the effectiveness of the proposed method.

[1]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[2]  A. Morse,et al.  Stability of switched systems with average dwell-time , 1999, Proceedings of the 38th IEEE Conference on Decision and Control (Cat. No.99CH36304).

[3]  Shengyuan Xu,et al.  Robust H∞ control for uncertain stochastic systems with state delay , 2002, IEEE Trans. Autom. Control..

[4]  Jun Wang,et al.  A general projection neural network for solving monotone variational inequalities and related optimization problems , 2004, IEEE Transactions on Neural Networks.

[5]  Alla Borisyuk,et al.  UNDERSTANDING NEURONAL DYNAMICS BY GEOMETRICAL DISSECTION OF MINIMAL MODELS , 2005 .

[6]  Daniel W. C. Ho,et al.  State estimation for delayed neural networks , 2005, IEEE Transactions on Neural Networks.

[7]  Kristina J. Nielsen,et al.  Dissociation Between Local Field Potentials and Spiking Activity in Macaque Inferior Temporal Cortex Reveals Diagnosticity-Based Encoding of Complex Objects , 2006, The Journal of Neuroscience.

[8]  Anthony N. Burkitt,et al.  A review of the integrate-and-fire neuron model: II. Inhomogeneous synaptic input and network properties , 2006, Biological Cybernetics.

[9]  Anthony N. Burkitt,et al.  A Review of the Integrate-and-fire Neuron Model: I. Homogeneous Synaptic Input , 2006, Biological Cybernetics.

[10]  F. Qiu,et al.  Neural representation of transparent overlay , 2007, Nature Neuroscience.

[11]  James Lam,et al.  A New Criterion of Delay-Dependent Asymptotic Stability for Hopfield Neural Networks With Time Delay , 2008, IEEE Transactions on Neural Networks.

[12]  Ju H. Park,et al.  LMI optimization approach on stability for delayed neural networks of neutral-type , 2008, Appl. Math. Comput..

[13]  D. Xie,et al.  Asymptotical stabilisability of networked control systems: time-delay switched system approach , 2008 .

[14]  Gang Feng,et al.  Delay-Dependent $H_{\infty}$ and Generalized $H_{2}$ Filtering for Delayed Neural Networks , 2009, IEEE Transactions on Circuits and Systems I: Regular Papers.

[15]  Yurong Liu,et al.  State estimation for jumping recurrent neural networks with discrete and distributed delays , 2009, Neural Networks.

[16]  Chunyu Yang,et al.  Delay-dependent robust stability for Hopfield neural networks of neutral-type , 2009, Neurocomputing.

[17]  Choon Ki Ahn,et al.  Passive learning and input-to-state stability of switched Hopfield neural networks with time-delay , 2010, Inf. Sci..

[18]  C. Ahn.  An ℋ∞ approach to stability analysis of switched Hopfield neural networks with time-delay , 2010 .

[19]  Hongye Su,et al.  Improved Delay-Dependent Stability Condition of Discrete Recurrent Neural Networks With Time-Varying Delays , 2010, IEEE Transactions on Neural Networks.

[20]  Jinde Cao,et al.  Stability analysis for stochastic neural networks of neutral type with both Markovian jump parameters and mixed time delays , 2010, Neurocomputing.

[21]  Peng Shi,et al.  Passivity Analysis for Discrete-Time Stochastic Markovian Jump Neural Networks With Mixed Time Delays , 2011, IEEE Transactions on Neural Networks.

[22]  Peng Shi,et al.  Delay-dependent exponential stability analysis for discrete-time switched neural networks with time-varying delay , 2011, Neurocomputing.

[23]  G. Duan,et al.  Stabilising slow-switching laws for switched discrete-time linear systems , 2011 .

[24]  Choon Ki Ahn.  Exponentially convergent state estimation for delayed switched recurrent neural networks , 2011, The European physical journal. E, Soft matter.

[25]  Peng Shi,et al.  Delay-Dependent Stability Analysis for Switched Neural Networks With Time-Varying Delay , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[26]  Yi Dong,et al.  Estimating Parameters of Generalized Integrate-and-Fire Neurons from the Maximum Likelihood of Spike Trains , 2011, Neural Computation.

[27]  Wei Xing Zheng,et al.  Stochastic state estimation for neural networks with distributed delays and Markovian jump , 2012, Neural Networks.

[28]  P. Balasubramaniam,et al.  Delay-dependent passivity criteria for uncertain switched neural networks of neutral type with interval time-varying delay , 2012 .

[29]  Li Yu,et al.  Passivity analysis for discrete-time switched neural networks with various activation functions and mixed time delays , 2011, Nonlinear Dynamics.

[30]  C. Ahn.  Switched exponential state estimation of neural networks based on passivity theory , 2012 .

[31]  Choon Ki Ahn.  Linear Matrix Inequality Optimization Approach to Exponential Robust Filtering for Switched Hopfield Neural Networks , 2012, J. Optim. Theory Appl..

[32]  Nikola Kasabov,et al.  Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition. , 2013, Neural networks : the official journal of the International Neural Network Society.

[33]  Peng Shi,et al.  Stochastic Synchronization of Markovian Jump Neural Networks With Time-Varying Delay Using Sampled Data , 2013, IEEE Transactions on Cybernetics.

[34]  S. Zhong,et al.  Finite-time H∞ control for a class of Markovian jump systems with mode-dependent time-varying delay , 2013, Advances in Difference Equations.

[35]  C. Low,et al.  An environment-dependent modulation of cortical neural response by forebrain cholinergic neurons in awake rat , 2013, Brain Research.