Machine Learning (SS 2020)
The course is closed!
Comment
Dear students,
due to the current situation regarding COVID-19 an in-person instruction cannot take place and courses shall be offered online, so is the material for our course 'Machine Learning' also available on online platforms and we try our best to make the experience as good as possible for you.
We will provide materials and recordings of the lecture as well as for the tutorials and request you not to distribute the materials over other channels then the ones we are using. In case you have any troubles in accessing anything, don't hesitate to contact us and we will find a solution. In general you should be able to access all platforms via your LMU-credentials (with our without "@campus.lmu.de"). With the LMU-credentials you can login to the systems uni2work, moodle and lmu-cast.
Please also note our organization slides (video on LMU-Cast: Link) where you will find additional information for our course.
Your ML-Team
Notes on Privacy Policy:
Moodle, LMU-Cast and Uni2Work
Moodle, LMU Cast and Uni2Work are websites from the Ludwig-Maximilians-Universität München and follow the privacy policy which can be read here: https://www.en.uni-muenchen.de/funktionen/privacy/index.html
YouTube
We are maintaining an online presence on YouTube to present our service and to communicate with our students in form of lecture recordings.YouTube is a service of Google Ireland Limited, Gordon House, Barrow Street, Dublin 4, Ireland, a subsidiary of Google LLC, 1600 Amphitheater Parkway, Mountain View, CA 94043 USA.
We would like to point out that this might cause user data to be processed outside the European Union, particularly in the United States. This may increase risks for users that, for example, may make subsequent access to the user data more difficult. We also do not have access to this user data. Access is only available to YouTube. Google LLC is certified under the Privacy Shield and committed to comply with European privacy standards.
https://www.privacyshield.gov/participant?id=a2zt000000001L5AAI&status=Active
The YouTube privacy policy can be found here:https://policies.google.com/privacy
News
- 15/05/2020: Details about the final examination are provided on moodle.
- 22/04/2020: Please note the enrollment formalities in Uni2Work (for Moodle and LMU-Cast)
- 20/04/2020: A video regarding the organization in this summer term has been uploaded: Link
- 17/04/2020: Please note the additional information on the organization of this course during the digital semester.
- 23/03/2020: (closed)The registration for this course via Uni2Work will be open from April 1st, 2020 till June 1st.
Organization
- Course: 3+2 hours weekly (equals 6 ECTS)
- Contact information no more available
- Required: Professional skill of at least one programming language
- Audience: The course is directed towards master students in informatics, bioinformatics and media informatics
- Course Language: English
- Registration closed (from April 1st, 2020 till June 1st, 2020)
- Organization slides: Link
- Organization video: Link
Time and Locations
All times are c.t. (cum tempore)
| Component | Where | Starts at |
| Lecture | YouTube | 23.04.2020 |
| Tutorial | LMU-Cast | 28.04.2020 |
Content
Machine Learning is a data-driven approach for the development of technical solutions. Initially motivated by the adaptive capabilities of biological systems, machine learning has increasing impact in many fields, such as vision, speech recognition, machine translation, and bioinformatics, and is a technological basis for the emerging field of Big Data.
The lecture will cover:
- Supervised learning: the goal here is to learn functional dependencies for classification and regression. We cover linear systems, basis function approaches, kernel approaches and neural networks. We will cover the recent developments in deep learning which lead to exciting applications in speech recognition and vision.
- Unsupervised Learning: the goal here is to compactly describe important structures in the data. Typical representatives are clustering and principal component analysis
- Graphical models (Bayesian networks, Markov networks), which permit a unified description of high-dimensional probabilistic dependencies
- Reinforcement Learning as the basis for the learning-based optimization of autonomous agents
- Some theoretical aspects: frequentist statistics, Bayesian statistics, statistical learning theory
The technical topics will be illustrated with a number of real-world applications.
Course Materials
| Date | Topic | VoD |
|---|---|---|
| 17/4/2020 | Organization | Link |
Final Examination
Informations regarding the final exams are sent via mail and can also be looked up on moodle.
Please note: There will be no second exam!
Recommended Literature:
- Deep Learning. Ian Goodfellow, Yoshua Bengio and Aaron Courville
- The Elements of Statistical Learning: Data mining, Inference and Prediction. Hastie, Tibshirani, Friedman
- Machine Learning: a Probabilistic Perspective. Kevin Murphy
- Bayesian Reasoning and Machine Learning. David Barber
- Pattern Recognition and Machine Learning. Christopher M. Bishop
- Artificial Intelligence: A Modern Approach. Russel and Norvig
Links to Tutorials
- Introduction to Python: Dive Into Python 3
- Introduction to PyTorch: Basics of PyTorch
- Playground TensorFlow