Website
Modulhandbuch ab WS 2020/21

Modul CS4295-KP04

Deep Learning (DEEPL)

Dauer:


1 Semester
Angebotsturnus:


Jedes Wintersemester
Leistungspunkte:


4
Studiengang, Fachgebiet und Fachsemester:
  • Master Medieninformatik 2020 (Wahlpflicht), Wahlpflicht, Beliebiges Fachsemester
  • Master Medizinische Ingenieurwissenschaft 2020 (Wahlpflicht), Wahlpflicht, Beliebiges Fachsemester
  • Master Entrepreneurship in digitalen Technologien 2020 (Wahlpflicht), Wahlpflicht, Beliebiges Fachsemester
  • Master Biophysik 2023 (Wahlpflicht), Wahlpflicht, Beliebiges Fachsemester
  • Master Psychologie 2016 (Wahlpflicht), Wahlpflicht, Beliebiges Fachsemester
Lehrveranstaltungen:
  • CS4295-V: Deep Learning (Vorlesung, 2 SWS)
  • CS4295-Ü: Deep Learning (Übung, 2 SWS)
Workload:
  • 75 Stunden Selbststudium
  • 45 Stunden Präsenzstudium
Lehrinhalte:
  • Foundations and Deep Learning Basics (Learning Paradigms, Classification and Regression, Underfitting and Overfitting)
  • Shallow Neural Networks (Basic Neuron Model, Multilayer Perceptions, Backpropagation, Computational Graphs, Universal Approximation Theorem, No-Free Lunch Theorems, Inductive Biases)
  • Optimization (Stochastic Gradient Descent, Momentum Variants, Adaptive Optimizer)
  • Convolutional Neural Networks (1D Convolution, 2D Convolution, 3D Convolution, ReLUs and Variants, Down and Up Sampling Techniques, Transposed Convolution)
  • Regularization (Early Stopping, L1 and L2 Regularization, Label Smoothing, Dropout Strategies, Batch Normalization)
  • Very Deep Networks (Highway Networks, Residual Blocks, ResNet Variants, DenseNets)
  • Dimensionality Reduction (PCA, t-SNE, UMAP, Autoencoder)
  • Generative Neural Networks (Variational Autoencoder, Generative Adversarial Networks, Diffusion Models)
  • Graph Neural Networks (Graph Convolutional Networks, Graph Attention Networks)
  • Fooling Deep Neural Networks (Adversarial Attacks, White Box and Black Box Attacks, One-Pixel Attacks)
  • Physics-Aware Deep Learning (Physical Knowledge as Inductive Bias, PINN, PhyDNet, Neural ODE, FINN)
Qualifikationsziele/Kompetenzen:
  • Students get a fundamental understanding deep learning basics such as backpropagation, computational graphs, and auto-differentiation
  • Students understand the implications of inductive biases
  • Students get a comprehensive understanding of most relevant deep learning approaches
  • Students learn to analyze the challenges in deep learning tasks and to identify well-suited approaches to solve them
  • Students will understand the pros and cons of various deep learning models
  • Students know how to analyze the models and results, to improve the model parameters, and to interpret the model predictions and their relevance
Vergabe von Leistungspunkten und Benotung durch:
  • Klausur oder mündliche Prüfung nach Maßgabe des Dozenten
Modulverantwortlicher:
  • Prof. Dr. Sebastian Otte
Lehrende:
  • MitarbeiterInnen des Instituts
  • Prof. Dr. Sebastian Otte
Literatur:
  • Goodfellow, I., Bengio, Y., & Courville, A. (2016): Deep Learning - MIT Press. ISBN 978-0262035613
  • Prince, S. J. D. (2023): Understanding Deep Learning - The MIT Press. ISBN 978-0262048644
  • Deisenroth, M. P., Faisal, A. A., & Ong, C. S. (2020): Mathematics for Machine Learning - Cambridge University Press, 2020. ISBN 978-1108470049
  • Bishop, C. M. (2006): Pattern Recognition and Machine Learning - Springer. ISBN 978-0387310732
  • Recent publications on the related topics:
Sprache:
  • Wird nur auf Englisch angeboten
Bemerkungen:

Admission requirements for taking the module:
- None

Admission requirements for participation in module examination(s):
- Successful completion of exercise assignments as specified at the beginning of the semester

Module Exam(s):
- CS4295-L1: Deep Learning, exam, 90 min

Letzte Änderung:
11.4.2024

Modulhandbuch online

Zur Liste aller Module