Johannes Schmidt-Hieber, Twente: Towards a statistical foundation of deep learning (Oberseminar Mathematische Stochastik)
Wednesday, 22.01.2020 17:00 im Raum SRZ 117
Recently a lot of progress has been made in the theoretical understanding of deep learning. One of the very promising directions is the statistical approach, which interprets deep learning as a statistical method and builds on existing techniques in mathematical statistics to derive theoretical error bounds. The talk surveys this field and describes future challenges.