University of Heidelberg, Applied Analysis Seminar
Thu 20.01.2022
14:15, posted in Applied Analysis
Dr. Giovanni S. Alberti (Uni Genoa)
Instability of machine learning
Online via ZOOM

Many of the breakthroughs of the last years in the applied sciences have been due to recent advances of machine learning, and in particular to deep learning. However, these methods have been shown to be unstable and susceptible to adversarial perturbations and deformations: a small error in the input may yield a large error in the output. In this talk, after a brief review of these phenomena, I will discuss its implications to the use of machine learning methods in inverse problems and imaging.

<< Back