    Course module   NWINM048C  Category   MA (Master)  Language of instruction   English  Offered by   Radboud University; Faculty of Science; Wiskunde, Natuur en Sterrenkunde;  Lecturer(s)     Academic year   2017   Period   KW1KW2  (04/09/2017 to 04/02/2018) 
 Starting block   KW1  
 Course mode   fulltime  
 Remarks     Registration using OSIRIS   Yes  Course open to students from other faculties   Yes  Preregistration   No  Waiting list   No  Placement procedure    
     
The aim of the course is to familiarize the student with the modern concepts of machine learning at the international research level. In particular:
 The student understands the concepts of Bayesian inference and use it to derive a number of different machine learning methods, such as sparse regression models, multilayered perceptrons, graphical models and Boltzmann Machines
 The student is familiar with learning algorithms based on the maximum likelihood principle and Bayesian posterior estimation
 The student is familiar with stochastic networks of interacting variables, thermodynamic concepts, and Monte Carlos sampling methods
 The student is familiar with a number of approximate inference methods, such as the variational mean field method, belief propagation
 The student is familiar with optimal control theory, stochastic optimal control theory and path integral control theory
 The student is capable to write computer programs to implement the above methods


The course provides an advanced introduction to the modern view on machine learning with emphasis on the Bayesian perspective. The course is intended for Master's students in physics as well as master's students in artificial intelligence/computer science with sufficient mathematical background. For artificial intelligence/computer science students it is highly recommended to to take the course Statistical machine learning prior to this course.
For physics and math students, this course is the followup of the bachelor course Inleiding Machine Learning
The course provides a good preparation for a Masters' specialisation in Theoretical Neuroscience or Machine Learning.




• David MacKay, Information Theory, Inference and Learning Algorithms, Cambridge University press. The entire book can be viewed onscreen at http://www.inference.phy.cam.ac.uk/mackay/itila/book.html • Several handouts will be distributed during the course 
• 32 hours lecture • 32 hours problem session Extra information teaching methods: • 28 hours lectures that will be given mostly by the students, with teacher's clarification when necessary • 28 hours of mathematical exercises and computer exercises 
See the course website: http://www.snn.ru.nl/~bertk/machinelearning/ 
Examination is weighted average of homework assignments and presentations. http://www.snn.ru.nl/~bertk/machinelearning 
The following courses are useful but not required: Voortgezette Kansrekening 
   Required materialsBookDavid MacKay, Information Theory, Inference and Learning Algorithms, Cambridge University press. The entire book can be viewed onscreen at http://www.inference.phy.cam.ac.uk/mackay/itila/book.html 
 HandoutsSeveral handouts will be distributed during the course 


Instructional modesCourse occurrence
 Lecture
 Tutorial

 TestsTentamenTest weight   1 
Opportunities   Block KW2, Block KW3 


  
 
 