The Mathematics of Reliable AI: Successes, Limitations, and Next Generation Computing
The Mathematics of Reliable AI: Successes, Limitations, and Next Generation Computing
-
Gitta Kutyniok, Ludwig-Maximilians-Universität München
Fine Hall 314
The new wave of artificial intelligence is impacting industry, public life, and the sciences in an unprecedented manner. However, one current major drawback is the lack of reliability as well as the enormous energy problem of AI.
The goal of this lecture is to first provide an introduction into this new vibrant research area, and showcase some recent successes. We will then focus on limitations of reliability of AI from a mathematical perspective, in particular, with respect to computability problems caused by current (digital) hardware. This will lead us naturally to novel approaches for future AI computing such as neuromorphic computing and spiking neural networks as the associated type of neural networks."