Second Order Spiking Perceptron

According to the usual approximation scheme, we present a more biologically plausible so-called Second Order Spiking Perceptron with renewal process inputs, which employs both first and second statistics, i.e. the means, variances and correlations of the synaptic input. We show that such perceptron, even a single neuron, is able to perform complex non-linear tasks like the XOR problem, which is impossible to be solved by traditional single-layer perceptrons. Here such perceptron offers a significant advantage over classical models, in that it includes the second order statistics in computations, and that it introduces variance in the error representation. We are to open up the possibility of carrying out a random computation in neuronal networks.

[1]  Adrienne L. Fairhall,et al.  Efficiency and ambiguity in an adaptive neural code , 2001, Nature.

[2]  L. Abbott,et al.  Synaptic Depression and Cortical Gain Control , 1997, Science.

[3]  T. Sejnowski,et al.  Correlated neuronal activity and the flow of neural information , 2001, Nature Reviews Neuroscience.

[4]  Jianfeng Feng,et al.  Dynamics of moment neuronal networks. , 2006, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[6]  H. Tuckwell.  Introduction to Theoretical Neurobiology: Linear Cable Theory and Dendritic Structure , 1988 .

[7]  Jianfeng Feng,et al.  Computational neuroscience , 1986, Behavioral and Brain Sciences.

[8]  Jianfeng Feng,et al.  Responses of Magnocellular Neurons to Osmotic Stimulation Involves Coactivation of Excitatory and Inhibitory Input: An Experimental and Theoretical Analysis , 2001, The Journal of Neuroscience.

[9]  R. Stein.  Some models of neuronal variability. , 1967, Biophysical journal.

[10]  Jianfeng Feng,et al.  Optimal control of neuronal activity. , 2003, Physical review letters.

[11]  Henry C. Tuckwell,et al.  Introduction to theoretical neurobiology , 1988 .

[12]  H. Sompolinsky,et al.  Population coding in neuronal systems with correlated noise. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[13]  P. Matthews.  Relationship of firing intervals of human motor units to the trajectory of post‐spike after‐hyperpolarization and synaptic noise. , 1996, The Journal of physiology.

[14]  Wulfram Gerstner,et al.  Spiking Neuron Models , 2002 .

[15]  Jianfeng Feng,et al.  Impact of Correlated Inputs on the Output of the Integrate-and-Fire Model , 2000, Neural Computation.

[16]  Xuyan Xiang,et al.  Spike-Rate Perceptrons , 2008, 2008 Fourth International Conference on Natural Computation.

[17]  Jianfeng Feng,et al.  Impact of Poisson synaptic inputs with a changing rate on weak-signal processing , 2003 .

[18]  Nicolas Brunel,et al.  Dynamics of Sparsely Connected Networks of Excitatory and Inhibitory Spiking Neurons , 2000, Journal of Computational Neuroscience.

[19]  V.P. Plagianakos,et al.  Spiking neural network training using evolutionary algorithms , 2005, Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005..