Rima Alaifari: Katalogdaten im Herbstsemester 2022

NameFrau Prof. Dr. Rima Alaifari
LehrgebietAngewandte Mathematik
Adresse
Seminar für Angewandte Mathematik
ETH Zürich, HG G 59.2
Rämistrasse 101
8092 Zürich
SWITZERLAND
Telefon+41 44 632 32 00
E-Mailrima.alaifari@sam.math.ethz.ch
URLhttp://www.sam.math.ethz.ch/~rimaa
DepartementMathematik
BeziehungAssistenzprofessorin

NummerTitelECTSUmfangDozierende
401-4661-DRLRobustness of Deep Neural Networks Belegung eingeschränkt - Details anzeigen
Only for ZGSM (ETH D-MATH and UZH I-MATH) doctoral students. The latter need to register at myStudies and then send an email to Link with their name, course number and student ID. Please see Link
2 KP2G + 1AR. Alaifari
KurzbeschreibungWhile deep neural networks have been very successfully employed in classification problems, their stability properties remain still unclear. In particular, the presence of adversarial examples has demonstrated that state-of-the-art networks are vulnerable to small perturbations in the data. This course serves as an introduction to adversarial attacks and defenses for deep neural nework algorithms.
Lernziel1. Theory: in this course, we will discuss the trade-off between accuracy and stability of classification algorithms and study the state-of-the-art for robust image classification, adversarial attacks and adversarial training.
2. Practice: students will train and attack deep neural networks themselves, to get a hands-on experience.
Voraussetzungen / BesonderesCourses on linear algebra, optimization and machine learning. Basic programming skills in Python, and experience with PyTorch or TensorFlow.
401-4661-72LRobustness of Deep Neural Networks6 KP2G + 1AR. Alaifari
KurzbeschreibungWhile deep neural networks have been very successfully employed in classification problems, their stability properties remain still unclear. In particular, the presence of adversarial examples has demonstrated that state-of-the-art networks are vulnerable to small perturbations in the data. This course serves as an introduction to adversarial attacks and defenses for deep neural nework algorithms.
Lernziel1. Theory: in this course, we will discuss the trade-off between accuracy and stability of classification algorithms and study the state-of-the-art for robust image classification, adversarial attacks and adversarial training.
2. Practice: students will train and attack deep neural networks themselves, to get a hands-on experience.
Voraussetzungen / BesonderesCourses on linear algebra, optimization and machine learning. Basic programming skills in Python and experience with PyTorch.
401-5650-00LZurich Colloquium in Applied and Computational Mathematics Information 0 KP1KR. Abgrall, R. Alaifari, H. Ammari, R. Hiptmair, S. Mishra, S. Sauter, C. Schwab
KurzbeschreibungResearch colloquium
Lernziel