SpikeCell: a deterministic spiking neuron

We present a model of spiking neuron that emulates the output of the usual static neurons with sigmoidal activation functions. It allows for hardware implementations of standard feedforward networks, trained off-line with any classical learning algorithm (i.e. back-propagation and its variants). The model is validated on hand-written digits recognition, and image classification tasks. A digital architecture is proposed and evaluated. The area needed for implementing the spiking neuron on a chip is 10 times smaller than that for the corresponding static neuron. The accuracy of the network's output increases with time, and reaches that of the emulated static neural network after an adequate integration period. Single errors in the spike trains, or interruption of the relaxation process, due for example to irradiation in harsh environments, are harmless.