Neural coding: adapting spike generation for embedded hardware classification
Résumé
Recent literature considers that Spiking Neural Networks are now a serious alternative of Formal Neural Networks
for embedded artificial intelligence. The changes in the information coding and the elementary neural computation make
them more efficient than FNNs in terms of power consumption and chip surface occupation. However, these results are often based on simple neural network topologies with basic data-sets. In this paper, we study the behavior of Spiking Convolutional Neural Networks when applied to two different classification tasks. To do so, we analyze the spiking activity on both MNIST and GTSRB data-sets using different rate-based and temporal coding schemes. Notably, the Spike Select method is confronted to First Spike and Jittered Periodic methods in terms of prediction accuracy and spiking activity. Finally, we conclude about spike generation within spiking CNNs for embedded hardware classification.