[IAML] - [2024Winter] - [en] - [Advanced Machine Learning]


Advanced Machine Learning [2024 SoSe]
Code
IAML
Name
Advanced Machine Learning
CP
8
Duration
one semester
Offered
follows *Fundamentals of Machine Learning*
Format
Lecture 4 SWS + Exercise course 2 SWS
Workload
240h, thereof
60h lecture
90h tutorials, homework, lecture wrap-up
90h graded final report
Availability
cannot be combined with *Machine Learning*
M.Sc. Angewandte Informatik
M.Sc. Data and Computer Science
M.Sc. Scientific Computing
Language
English
Lecturer(s)
Ullrich Köthe
Examination scheme
Learning objectives Students get to know advanced machine learning methods that define the state-of-the-art and major research directions in the field. Students understand when these methods are called for, what limitations of standard solutions they address, and how they are applied to real-world problems.
In addition, students learn how to use Python-based machine learning software such as scikit-learn, theano and OpenGM.
Learning content The lecture, along with its sibling *Fundamentals of Machine Learning*, offers an extended version of the one-semester course *Machine Learning*:
Multi-layered architectures (neural networks, deep learning); directed and undirected probabilistic graphical models (Gaussian processes, latent variable models, Markov random fields, structured learning); feature optimization (feature selection and learning, dictionary learning, kernel approximation, randomization); weak supervision (one-class learning, multiple instance learning, active learning, reinforcement learning)
Requirements for participation recommended are: lecture *Fundamentals of Machine Learning* or similar
Requirements for the assignment of credits and final grade The module is completed with a graded written examination. This examination is a report on a 90 h mini-research project. The final grade of the module is determined by the grade of the examination. The requirements for the assignment of credits follows the regulations in section modalities for examinations. Details will be given by the lecturer.
Useful literature David Barber: Bayesian Reasoning and Machine Learning, Cambridge University Press, 2012
Christopher M. Bishop: Pattern Recognition and Machine Learning, Springer, 2006