FS2021: 31088/61088 Advanced Topics in Machine Learning

This course provides an introduction to Deep Learning methods. These are modern methods in artificial intelligence (AI), which are today incorporated in most of the top-performing algorithms in several fields of research. We focus on the machine learning paradigm, where rules are learned from examples, rather than being hard-coded. Most examples will be in computer vision, that is, about problems of object recognition, detection, segmentation in images and videos. On a successful completion of this course you can expect to be able to develop intelligent software to automate routine labor, understand images and videos (but you should be able to work with other data too), and support basic scientific research.

Allgemeine Informationen

Kursbeschreibung
The course will be held online.
Lectures and tutorials will be given live during the day and times as in the official schedule.
Podcasts of the lectures and tutorials will be posted in ILIAS.
Currently there are podcasts from last year that some might find useful to prepare in advance.


The zoom link to attend the lectures and tutorials is

https://us02web.zoom.us/j/88157161793?pwd=Qjhad2thU2NWMzh0a1RPdHZtYlNnQT09
Please post questions and discussion about the lecture, tutorial and assignments on the Piazza forum:
https://piazza.com/class/kls3kb90zdl5fa
Kursprogramm
This course provides an introduction to Deep Learning methods. These are modern methods in artificial intelligence (AI), which are today incorporated in most of the top-performing algorithms in several fields of research. We focus on the machine learning paradigm, where rules are learned from examples, rather than being hard-coded.
Most examples will be in computer vision, that is, about problems of object recognition, detection, segmentation in images and videos.

The course will cover most of the contents of the Deep Learning book by Goodfellow et al.:
review of Machine Learning,
Deep feedforward networks (anatomy of a neural network, gradient-based learning,
back-propagation, regularization, optimization, training),
Convolutional Neural Networks,
Recurrent Neural Networks,
Autoencoders,
Representation learning.
Sefl-Supervised Learning/Transfer Learning.

Prerequisites: applied math fundamentals like linear algebra, probability and numerical optimization

Books
[STRICTLY FOLLOWED] Deep Learning by Ian Goodfellow, Yoshua Bengio, Aaron Courville (available online at www.deeplearningbook.org)
[REFERENCES] Neural Networks and Deep Learning by Michael Nielsen (free online book at www.neuralnetworksanddeeplearning.com)
[ADDITIONAL EXCELLENT RESOURCE] Pattern Recognition and Machine Learning by Christopher M. Bishop
Zielgruppe
On successful completion of this course students are expected to:
1) be able to formalize tasks in computer vision via neural networks
2) design neural networks to solve data-rich tasks
3) build datasets, tune and train neural networks with advanced deep learning libraries
4) understand the inner mechanisms of neural networks during training
5) analyze the performance of neural networks on tasks of interest

Allgemein

Sprache
Englisch
Copyright
All rights reserved

Verfügbarkeit

Zugriff
Unbegrenzt – wenn online geschaltet
Aufnahmeverfahren
Sie können diesem Kurs direkt beitreten.
Zeitraum für Beitritte
Unbegrenzt

Für Kursadministration freigegebene Daten

Daten des Persönlichen Profils
Anmeldename
Vorname
Nachname
E-Mail