To introduce the student to new trends in statistical signal processing and machine learning.

• Comprehend and apply advanced methods within machine learning
• Collect scientific knowledge and data related to topics covered in the course
• Formulate and carry out a mini-project related to one or more of the covered course topics (preferably within the scope of the student’s PhD project)
• Design a complex machine learning system based on an analysis of the problem and the project aims
• Implement the machine learning system
• Evaluate the performance of the machine learning system
• Assess and summarize the mini-project results in relation to aims, methods and available data
• Disseminate the project results in a technical report

The course introduces new trends and advanced topics in machine learning. The course covers key topics in machine learning including Bayesian parametric and non-parametric inference, optimization, low rank approximations and kernel methods. The course consists of lectures and exercises, and is followed up by a mini-project presented in a written report. We encourage that students apply the methods taught to data relevant for their PhD project. Current possible topics are: Bayesian methods, latent variable modeling, sparse representations and kernel methods. Typical applications include: Bio-medical, audio, multimedia, and topic modeling as well as collaborative filtering and monitoring systems.