0000003105 20W 2SWS SE Master-Seminar - Beyond Deep Learning: Selected Topics on Novel Challenges (IN2107, IN4408)   Hilfe Logo

LV - Detailansicht

Wichtigste Meldungen anzeigenMeldungsfenster schließen
Allgemeine Angaben
Master-Seminar - Beyond Deep Learning: Selected Topics on Novel Challenges (IN2107, IN4408) 
Wintersemester 2020/21
Informatik 9 - Lehrstuhl für Bildverarbeitung und Künstliche Intelligenz (Prof. Cremers)
Angaben zur Abhaltung
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
- Real world datasets

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:

You should already have a good understanding of basic machine learning & deep learning concepts & models. Especially,they are required to have taken at least 1 machine learning related course such as:
-Introduction to Deep Learning
-Introduction to Machine Learning
-Machine Learning for CV
-Advanced Deep Learning for CV/Robotics
-Probabilistic Graphical Models in CV
You should be able to take initiatives to plan & maintain a continuous workflow&communicate with tutors efficiently.
As 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's crucial for interested applicants to also send us an mail (bdlstnc-ws20@vision.in.tum.de) demonstrating their interest & fulfillment of prerequisites.Details will be explained during the pre-course meeting & available on the course website. Places will be assigned through the matching system.
Upon completion of this module, students will have acquired experience in writing scientific papers and presenting them.

The lectures will be devoted to theoretical and practical deep learning concepts. Throughout this course, students will work on projects consisting of real problems. Regular communication with experienced tutors will ensure that appropriate approaches are used and learning objectives are attained.
Für die Anmeldung zur Teilnahme müssen Sie sich in TUMonline als Studierende/r identifizieren.
Anmerkung: Places will be assigned through the TUM matching system (http://matching.in.tum.de).
- 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