6. From Activations to Spikes

By Francesco Galluppi, Gensight Biologics, France | Teresa Serrano Gotarredona, Instituto de Microelectrónica de Sevilla, Spain | Qian Liu, aiCTX, Zurich, Switzerland | Evangelos Stromatias, Medis Medical Imaging Systems, The Netherlands

Published: 31 Mar 2020

© 2020 Francesco Galluppi | Teresa Serrano Gotarredona | Qian Liu | Evangelos Stromatias

Abstract

Deep learning is not new ‘magic’, but rather has a history over a few decades. An overview of some popular Artificial Neural Networks (ANNs) is offered below. The rest of the chapter reveals how one can use the application-focused insights from Deep Neural Networks (DNNs) to engineer SNNs and an approach to convert pre-trained networks to use spikes.