|
Deep Learning (DL)
- Lecturer
- Prof. Dr.-Ing. habil. Andreas Maier
- Details
- Vorlesung
2 cred.h, ECTS studies, ECTS credits: 2,5
nur Fachstudium, Sprache Englisch
Time and place: Wed 8:30 - 10:00, room tbd; comments on time and place: new room: RZ 2.049
- Fields of study
- WPF INF-MA ab 1
WPF MT-MA-BDV 1
- Prerequisites / Organisational information
- The following lectures are recommended:
- Contents
- 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.
- Recommended literature
- 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)
- ECTS information:
- Credits: 2,5
- Additional information
- Keywords: deep learning; machine learning
Expected participants: 60, Maximale Teilnehmerzahl: 60
www: http://www5.cs.fau.de/lectures/ss-18/deep-learning-dl/ Registration is required for this lecture. Die Registration via: mein Campus
- Assigned lectures
- UE: Deep Learning Exercises
-
Lecturers: Leonid Mill, M. Sc., Tobias Würfl, M. Sc., Katharina Breininger, M. Sc.
www: http://www5.cs.fau.de/lectures/ss-18/deep-learning-dl/
- Verwendung in folgenden UnivIS-Modulen
- Startsemester SS 2018:
- Deep Learning (DL)
- Department: Chair of Computer Science 5 (Pattern Recognition)
|
|
|