Incremental Neural Synthesis for Spiking Neural Networks

We present an iterative neural synthesis approach to train Convolutional Spiking Neural Networks for classification problems. Unlike previous neural synthesis methods which primarily compute the neuron firing rates, our method is designed to compute multiple spikes at arbitrary timings. As such, our approach is directly applicable to spatio-temporal problems using spiking network models. In our approach, each weight update is formulated as a linear Constraint Satisfaction Problem, which can then be solved using existing numerical techniques. On the MNIST, EMNIST, and ETH-80 image classification benchmarks, our approach demonstrates competitive with other models in the literature, while requiring relatively few training samples to converge to a good solution.