Seminar: Beyond Deep Learning: Selected Topics on Novel Challenges (5 ECTS)
Winter Semester 2021/2022, TU München
Organizers: Christian Tomani, Yuesong Shen, Prof. Dr. Daniel Cremers
E-Mail: bdlstnc-ws21@vision.in.tum.de
News
In order for participants to get matched to a topic, please send us an email to bdlstnc-ws21@vision.in.tum.de with the title “[Topic_Matching] <Firstname> <Lastname>”, and attach a filled topic preference form (rename to "firstname_lastname.xlsx") until October 25th. Download the template for topic preference form here: Topic preference template.
The Kick-Off meeting will take place on October 20th at 3:00pm in room 01.07.014.
The preliminary meeting took place on Wednesday July 7th at 3pm via Zoom. Slides are available here.
The registration is managed via the TUM matching system website help. If you like this course, consider giving it a high priority in the matching system.
To apply for this seminar and get a priority, please also send us an email to bdlstnc-ws21@vision.in.tum.de with the title “[Application] <Firstname> <Lastname>”, and attach your CV, transcript, and a filled course application form (rename to "firstname_lastname.xlsx"). Download the template for course application form here: Application template.
Course Description
Deep learning models nowadays provide state of the art results and set a new standard for many applications, such as speech recognition, computer vision, predicting patients’ states in medicine as well as time series forecasting in finance.
This course will be focusing on deep learning models. The topics will include:
- Time series models and post-calibration
- Bayesian deep learning models
- Graphical Models
- Alternative deep models and learning methods
- Metrics for evaluating uncertainty
We will be discussing state of the art research and open issues in the scientific community.
The time and location of the pre-course meeting will be announced on the course website:
Prerequisites
Participants should already have a good understanding of basic machine learning and deep learning concepts and models. Especially, they are required to have taken at least one machine learning related course such as:
- Introduction to Deep Learning
- Introduction to Machine Learning
- Machine Learning for Computer Vision
- Advanced Deep Learning for Computer Vision / Robotics
- Probabilistic Graphical Models in Computer Vision
- etc.
Participants should be able to take initiatives to plan and maintain a continuous workflow and communicate with tutors efficiently.
As many projects consider theoretical aspects of learning theory, a solid basis as well as interest for mathematics is highly recommended.
Prior experiences with machine learning projects are also a plus.
Note: it is crucial for interested applicants to also send us an e-mail (bdlstnc-ws21@vision.in.tum.de) demonstrating their interest and fulfillment of prerequisites. The details will be explained during the pre-course meeting and available on the course website.
Places will be assigned through the TUM matching system (http://matching.in.tum.de).
Course Structure
This course will be held as a block seminar.
Course Schedule
- Preliminary meeting: October 20th at 3pm, online, slides
- Kick-Off Meeting: October 20th at 3pm, seminar room 01.07.014
- Final Presentations: January 18th, 2022 from 1pm-4pm and January 19th, 2022 9am-4pm, possibly in person
Literature
- Deep Learning, Goodfellow, Bengio, Courville, 2016, http://www.deeplearningbook.org/
- Machine learning: a probabilistic perspective, Murphy, 2012
- The Elements of Statistical Learning, Hastie, Tibshirani, Friedman 2001
- Relevant papers will be announced during the course.