Study Guide@lith   Link to LiU Homepage
 

Linköping Institute of Technology

Link to LiU Homepage
 
Valid for year : 2011
 
TBMI26 Neural Networks and Learning Systems, 6 ECTS credits.
/Neuronnät och lärande system/

For:   BME   CS   D   I   Ii   IT   KeBi   Y  

 

Prel. scheduled hours: 56
Rec. self-study hours: 104

  Area of Education: Technology

Main field of studies: Biomedical Engineering, Electrical Engineering

  Advancement level (G1, G2, A): A

Aim:
The aim is that students after passing the course will be able to design and apply artificial neural networks and other learning systems for adaptive data analysis. Students will also be able to apply such methods in order to find meaningful relations in multidimensional signals where the degree of complexity makes traditional model-based methods unsuitable or impossible to use.

Specifically, students should be able to:
  • Explain the difference between particular learning paradigms
  • Implement and use common methods in those paradigms
  • Select an appropriate method for solving a given problem


Prerequisites: (valid for students admitted to programmes within which the course is offered)
Requisite: Algebra, Multivariable Calculus, Mathematical statistics. Recommended: Signal theory.

Note: Admission requirements for non-programme students usually also include admission requirements for the programme and threshhold requirements for progression within the programme, or corresponding.

Organisation:
Lectures, Exercises, Laboratory exercises (including an obligatory written report)

Course contents:
Classification: pattern recognition, discriminant functions; Supervised learning: the perceptron, the multi-layer perceptron, stochastic gradient search, error back-propagation; Unsupervised learning: principal component analysis (PCA), canonical correlation analysis (CCA), independent component analysis (ICA), competitive learning, self organizing maps (SOM), clustering; Content addressable memories: state spaces, Hopfield memories; Reinforcement learning: Markov models, Q-learning; Genetic methods: genetic algorithms, genes and schemas

Course literature:
S. Haykin, Neural Networks, second edition, Prentice Hall 1999
Compendium: examples, supplementary material, lab manual


Examination:
Written examination
Laboratory work
4 ECTS
2 ECTS
 



Course language is Swedish/English.
Department offering the course: IMT.
Director of Studies: Håkan Örman
Examiner: Magnus Borga
Link to the course homepage at the department


Course Syllabus in Swedish

Linköping Institute of Technology

Link to top of pagep


Contact: TFK , val@tfk.liu.se
Last updated: 10/27/2010