PIMS- SFU CSC Seminar: Graeme McCaig

An intriguing application of Deep Learning research is the use of Deep Convolutional Neural Networks (DCNNs) for image processing, as seen for example in the Prisma app and the Deep Dream algorithm. At SFU SIAT's iVizLab, we are using DCNNs within systems and experiments for augmenting and modeling the cognitive processes of human artists. In this talk I will overview the principles behind artistic image generation and stylization with DCNNs, examining several specific algorithms. I will also show some of iVizLab's current work in the area.