Events Calendar

Joint Math-FLDS/ CPS Seminar

Speaker: Reinhard Heckel, Department of Electrical and Computer Engineering Technical, University of Munich

Talk Title: Image Recovery and Recognition via Exploiting the Structural Bias of Neural Networks

Abstract: Deep neural networks are highly successful tools for image classification, recovery, and restoration. This success is often attributed to large amounts of training data. However, recent findings challenge this view and instead suggest that a major contributing factor to this success is that the architecture imposes strong prior assumptions-”so strong that it enables image recovery without any training data. In this talk we discuss two instances of this phenomena: First, we show that fitting a convolutional network to a corrupted and/or under-sampled measurement of an image provably removes noise and corruptions from that image, without ever having trained the network. Second, we show that it is possible to learn from a dataset with both true and false examples, obtained without explicit human annotations, by exploiting the phenomena that neural networks fit true examples faster than false ones.

Host: Mahdi Soltanolkotabi, soltanol@usc.edu

Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132

Audiences: Everyone Is Invited

Contact: Talyia White