|
Deep Learning (DL)5 ECTS (englische Bezeichnung: Deep Learning)
(Prüfungsordnungsmodul: Deep Learning)
Modulverantwortliche/r: Andreas Maier Lehrende:
Andreas Maier, Vincent Christlein
Start semester: |
WS 2020/2021 | Duration: |
1 semester | Cycle: |
halbjährlich (WS+SS) |
Präsenzzeit: |
60 Std. | Eigenstudium: |
90 Std. | Language: |
Englisch |
Lectures:
Empfohlene Voraussetzungen:
It is recommended to finish the following modules before starting this module:
Introduction to Pattern Recognition (WS 2019/2020)
Inhalt:
Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition and artificial intelligence, both from academia and industry.
This lecture introduces the core elements of neural networks and deep learning, it comprises:
(multilayer) perceptron, backpropagation, fully connected neural networks
loss functions and optimization strategies
convolutional neural networks (CNNs)
activation functions
regularization strategies
common practices for training and evaluating neural networks
visualization of networks and results
common architectures, such as LeNet, Alexnet, VGG, GoogleNet
recurrent neural networks (RNN, TBPTT, LSTM, GRU)
deep reinforcement learning
unsupervised learning (autoencoder, RBM, DBM, VAE)
generative adversarial networks (GANs)
weakly supervised learning
applications of deep learning (segmentation, object detection, speech recognition, ...)
The accompanying exercises will provide a deeper understanding of the workings and architecture of neural networks.
Lernziele und Kompetenzen:
The students
explain the different neural network components,
compare and analyze methods for optimization and regularization of neural networks,
compare and analyze different CNN architectures,
explain deep learning techniques for unsupervised / semi-supervised and weakly supervised learning,
explain deep reinforcement learning,
explain different deep learning applications,
implement the presented methods in Python,
autonomously design deep learning techniques and prototypically implement them,
effectively investigate raw data, intermediate results and results of Deep Learning techniques on a computer,
autonomously supplement the mathematical foundations of the presented methods by self-guided study of the literature,
discuss the social impact of applications of deep learning applications.
Literatur:
- Ian Goodfellow, Yoshua Bengio, Aaron Courville: Deep Learning. MIT Press, 2016.
Christopher Bishop: Pattern Recognition and Machine Learning, Springer Verlag, Heidelberg, 2006
Yann LeCun, Yoshua Bengio, Geoffrey Hinton: Deep learning. Nature 521, 436–444 (28 May 2015)
Weitere Informationen:
Keywords: deep learning; neural networks; pattern recognition; signal processing
www: http://www5.cs.fau.de/lectures/ws-1920/deep-learning-dl/
Verwendbarkeit des Moduls / Einpassung in den Musterstudienplan:
- Communications and Multimedia Engineering (Master of Science)
(Po-Vers. 2011 | TechFak | Communications and Multimedia Engineering (Master of Science) | Gesamtkonto | Wahlmodule | Technische Wahlmodule | Deep Learning)
Dieses Modul ist daneben auch in den Studienfächern "Advanced Signal Processing & Communications Engineering (Master of Science)", "Computational Engineering (Master of Science)", "Computational Engineering (Rechnergestütztes Ingenieurwesen) (Master of Science)", "Informatik (Master of Science)", "Information and Communication Technology (Master of Science)", "Informations- und Kommunikationstechnik (Master of Science)", "International Information Systems (IIS) (Master of Science)", "Mechatronik (Bachelor of Science)", "Mechatronik (Master of Science)", "Medizintechnik (Master of Science)" verwendbar. Details
Studien-/Prüfungsleistungen:
Deep Learning (Prüfungsnummer: 901895)
(englischer Titel: Deep Learning)
zugeh. "mein campus"-Prüfung: | - 901895 Deep Learning (Gewichtung: 100.0 %, Prüfung, Form: Klausur, Drittelnoten (mit 4,3), Dauer: 90, 5 ECTS, Prüfung).
|
- Prüfungsleistung, Klausur, Dauer (in Minuten): 90, benotet
- Anteil an der Berechnung der Modulnote: 100.0 %
- weitere Erläuterungen:
90-minütige schriftliche Prüfung über den Stoff der Vorlesung und der Übungen. 90 minute written exam about the lecture and the exercises.
- Prüfungssprache: Englisch
- Erstablegung: WS 2020/2021, 1. Wdh.: SS 2021
1. Prüfer: | Andreas Maier (100196) |
- Termin: 24.03.2021, 11:00 Uhr, Ort: BASPH
Termin: 26.07.2021, 17:00 Uhr, Ort: BASPH
Termin: 06.04.2022, 15:15 Uhr, Ort: s. Aushang
Termin: 08.08.2022
|
|
|