Self-aware AI: How can a neural network learn to say „I do not know“?

Industriegespräche Rhein/Neckar

Vortrag
Datum:
Mo, 23.11.2020 17:30  –   Mo, 23.11.2020 22:00
Sprecher:
Dr. Melih Kandemir, Bosch Center for Artificial Intelligence
Adresse:
Mathematik-Informatik-Station (MAINS)
Heidelberg Laureate Forum Foundation, Kurfürstenanlage 52, 69115 Heidelberg

 
Anmeldung erforderlich
Sprache:
Englisch
Veranstaltungspartner:
Heidelberg Laureate Forum Foundation, Heidelberger Institut für Theoretische Studien
Kontaktperson:
Dr. Andreas Fehlner,
DPG-Vereinigung:
Arbeitskreis Industrie und Wirtschaft (AIW)  Arbeitskreis Physik, moderne Informationstechnologie und Künstliche Intelligenz (AKPIK)  

Beschreibung

Deep learning stands at present as the most powerful generic tool
for developing intelligent systems. Deep neural nets have reached
unprecedented prediction accuracies, to the extent that they have
outperformed the best bioinformatics techniques in protein folding
prediction and the best language understanding methods in text
analysis without any domain knowledge. Neural networks owe their
success to their capability of memorizing data in a parametric way.
A successful neural network architecture typically has a larger
number of parameters than observations. This property causes a
severe artifact: Neural nets are not capable of propagating
uncertainty through their layers properly, thus they are not capable
of attributing sensible uncertainties to their predictions.
This causes a neural net trained on handwritten digits to assign
the picture of a cat to a random digit with high confidence, making
its safe and reliable use in industry scenarios questionable.

This talk will introduce the basics for uncertainty quantification
in neural nets, walk through a compilation of recent research
challenges in this area, and provide insights on key industry use
cases of uncertainty-aware AI methods.

Registration starts on Monday, 26. October.

------

Map with the event location:

MAINSwithLogo.png
MAINSwithLogo.png