Ort und Zeit
Seminar: Mo, 12-14 Uhr, online, -
Voranmeldung: per E-Mail an Diyora Salimova
Vorbesprechung 14.04., 15:00, über Zoom (bitte schreiben Sie der Dozentein, falls der Termin nicht passt)
Vortragsbesprechungen (Tutorium zum Seminar): Termine nach Vereinbarung
Lehre
Dozent:in: Diyora Salimova
Assistenz: Ilkhom Mukhammadiev
Sprache: Vortrag/Teilnahme auf Deutsch oder Englisch möglich
Inhalt
In recent years, deep learning have been successfully employed for a multitude of computational problems including object and face recognition, natural language processing, fraud detection, computational advertisement, and numerical approximations of differential equations. Such simulations indicate that neural networks seem to admit the fundamental power to efficiently approximate high-dimensional functions appearing in these applications.
The seminar will review some classical and recent mathematical results on approximation properties of deep learning. We will focus on mathematical proof techniques to obtain approximation estimates on various classes of data including, in particular, certain types of PDE solutions.
Vorkenntnisse
Grundlagen der Funktionalanalysis, der Numerik partieller Differentialgleichungen und der Wahrscheinlichkeitstheorie.
Verwendbarkeit
Wahlmodul im Optionsbereich (2HfB21)
Mathematisches Seminar (BSc21)
Wahlpflichtmodul Mathematik (BSc21)
Mathematische Ergänzung (MEd18)
Mathematisches Seminar (MSc14)
Wahlmodul (MSc14)
Mathematical Seminar (MScData24)
Elective in Data (MScData24)