The Properties of Spike-Rate Perceptron with Super-Poisson Input

We present the non-linear properties of Spike-Rate Perceptron with super-Poisson inputs, which employs both first and second statistical representation, i.e. the means, variances and correlations of the synaptic input. It shows that such perceptron, even a single neuron, is able to perform various complex non-linear tasks like the XOR problem. Here such perceptron offers a significant advantage over classical models, in that they include both the mean and the variance of the input signal.