Deep Learning [DL]

Dozentinnen/Dozenten:

Andreas Maier, Katharina Breininger, Sulaiman Vesal

Angaben:

Vorlesung, 2 SWS, ECTS: 2,5, nur Fachstudium

Termine:

Di, 8:30 - 10:00, H4

Studienrichtungen / Studienfächer:

WPF INF-MA ab 1
WPF MT-MA-BDV 1
WF CME-MA ab 1

Voraussetzungen / Organisatorisches:

The following lectures are recommended:

• Introduction to Pattern Recognition (IntroPR)

• Pattern Recognition (PR)

Application via https://www.studon.fau.de/crs2526786.html

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.

Empfohlene 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)

Schlagwörter:

deep learning; machine learning

Deep Learning Exercises [DL E]

Dozentinnen/Dozenten:

Leonid Mill, Hendrik Schröter

Angaben:

Übung, 2 SWS, ECTS: 2,5, nur Fachstudium

Studienrichtungen / Studienfächer:

WPF INF-MA ab 1
WF CME-MA ab 1

Schlagwörter:

deep learning; machine learning

HS Deep Learning for NLP [HSprakt]

Dozent/in:

Stefan Evert

Angaben:

Hauptseminar, 2 SWS, ECTS: 5, Bachelor

Termine:

Mi, 10:15 - 11:45, 01.019

Voraussetzungen / Organisatorisches:

Participants must register for the StudOn course linked below. Seminar places are assigned on a first come, first served basis.

Inhalt:

Deep neural networks – also known as deep learning – have attracted significant attention in recent years. They have had a transformative influence on natural language processing (NLP) and artificial intelligence (AI), with numerous success stories and even claims of superhuman learning performance in certain tasks. According to Young et al. (2017), more than 70% of the papers presented at recent NLP conferences made use of deep learning techniques.
This seminar will focus on the application of deep learning techniques to natural language processing tasks and on the topic "Social Bots: Danger or Myth?".

Empfohlene Literatur:

• Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, Pascal Vincent, Arxiv, 2012.

• Deep Learning, Yoshua Bengio, Ian Goodfellow, Aaron Courville, MIT Press

• Goldberg, Yoav (2017). Neural Network Methods for Natural Language Processing. Number 37 in Synthesis Lectures on Human Language Technologies. Morgan & Claypool.

• Young, Tom; Hazarika, Devamanyu; Poria, Soujanya; Cambria, Erik (2017). Recent trends in deep learning based natural language processing. CoRR, abs/1708.02709. http://arxiv.org/abs/1708.02709

• http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial

• http://deeplearning.net/tutorial/

• Stanford University CS 224: Deep Learning for NLP (http://cs224d.stanford.edu/)

• University of Oxford: Deep Natural Language Processing (https://github.com/oxford-cs-deepnlp-2017/lectures)

Seminar Deep Learning Theory & Applications [SemDL]

Dozentinnen/Dozenten:

Vincent Christlein, Stefan Evert, Ronak Kosti

Angaben:

Seminar, 4 SWS, benoteter Schein, ECTS: 5, nur Fachstudium

Termine:

Mi, 10:15 - 11:45, 01.019

Studienrichtungen / Studienfächer:

WPF INF-MA 1
WPF MT-MA-BDV 1
WPF CE-MA-TA-MT 1

Inhalt:

Deep Neural Networks or so-called deep learning has attracted significant attention in the recent years. They have had a transformative influence on Natural Language Processing (NLP) and Artificial Intelligence (AI), with numerous success stories recent claims of superhuman learning performance in certain tasks. According to Young et al. (2017), more than 70% of the papers presented at recent NLP conferences made use of deep learning techniques. Interestingly, the concept of Neural Networks inspired researchers already over generations since Minky's famous book (cf. http://en.wikipedia.org/wiki/Society_of_Mind ). Yet again, this technology brings researchers to the believe that Neural Networks will eventually be able to learn everything (cf. http://www.ted.com/talks/jeremy_howard_the_wonderful_and_terrifying_implications_of_computers_that_can_learn ).

This year's main topic is: „Social Bots: Danger or Myth?".

Empfohlene Literatur:

• Representation Learning: A Review and New Perspectives, Yoshua Bengio, Aaron Courville, Pascal Vincent, Arxiv, 2012.

• Deep Learning, Yoshua Bengio, Ian Goodfellow, Aaron Courville, MIT Press

• Goldberg, Yoav (2017). Neural Network Methods for Natural Language Processing. Number 37 in Synthesis Lectures on Human Language Technologies. Morgan & Claypool.

• Young, Tom; Hazarika, Devamanyu; Poria, Soujanya; Cambria, Erik (2017). Recent trends in deep learning based natural language processing. CoRR, abs/1708.02709. http://arxiv.org/abs/1708.02709

• Gradient-Based Learning Applied to Document Recognition, Yann Lecun, 1998

• Dropout: A Simple Way to Prevent Neural Networks from Overfitting, Srivastava et al. 2014

• Greedy layer-wise training of deep networks, Bengio, Yoshua, et al. Advances in neural information processing systems 19 (2007): 153.

• Reducing the dimensionality of data with neural networks, Hinton et al. Science 313.5786 (2006): 504-507.

• Training Deep and Recurrent Neural Networks with Hessian-Free Optimization, James Martens and Ilya Sutskever, Neural Networks: Tricks of the Trade, 2012.

• Deep Boltzmann machines, Hinton et al.

• Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion, Pascal Vincent et al.

• A fast learning algorithm for deep belief nets, Hinton et al., 2006

• ImageNet Classification with Deep Convolutional Neural Networks, Alex Krizhevsky, Ilya Sutskever, Geoffrey E Hinton, NIPS 2012

• Regularization of Neural Networks using DropConnect, Wan et al., ICML

• OverFeat: Integrated recognition, localization and detection using convolutional networks. Computing Research Repository, abs/1312.6229, 2013.

• http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial

• http://deeplearning.net/tutorial/

• Deep Learning Course on Coursera by Hinton

• DL platform with GPU support: caffe, lasagne, torch etc.

• Stanford University CS 224: Deep Learning for NLP (http://cs224d.stanford.edu )

• University of Oxford: Deep Natural Language Processing (https://github.com/oxford-cs-deepnlp-2017/lectures )

Schlagwörter:

deep learning; neural networks; machine learning; pattern recognition; natural language processing