Course contents *

Extension of theory and methodology for using multilayer perceptrons and error correction learning. More about learning theory and support vector machines (SVM). Basics about statistical methodology for learning systems and techniques based on “mixture of experts”. Use of attractor neural networks and SOM (Self-Organizing Maps) as associative memory and for clustering. Distributed and localized representation in neural networks, e.g. fuzzy representation and Gaussian mixtures. ANN for time series prediction. Development trends in brain-inspired algorithms and architectures.

A project where ANN is applied in practice on some larger problem involving classification, prediction, categorization, clustering and/or visualization.

Intended learning outcomes *

The goal of the course is to give the students

• more depth with regard to theory and methodology for some of the more common ANN-techniques
• experience from practical use of some ANN method on a larger problem
• more insight in development trends in the area of brain-inspired algorithms and architectures

so that they will be able to

• judge the applicability of and how to apply ANN
• critically evaluate results from studies using ANN
• to follow the future development of the ANN area.

Course Disposition

No information inserted

Specific prerequisites *

No information inserted

Recommended prerequisites

2D1432/DD2432 ANN and other learning systems.

Equipment

No information inserted

Literature

To be announced at least 2 weeks before course start at course web page. Similar courses have used e.g. Neural Networks – a comprehensive foundation by Simon Haykin

Grading scale *

A, B, C, D, E, FX, F

Examination *

• LAB1 - Laboratory Work, 1.5 credits, Grading scale: P, F
• PRO1 - Project, 3.0 credits, Grading scale: A, B, C, D, E, FX, F
• TEN1 - Examination, 1.5 credits, Grading scale: P, F

Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.

The examiner may apply another examination format when re-examining individual students.

Other requirements for final grade *

Examination (TEN1; 1,5 university credits).
Laboratory assignments (LAB1; 1,5 university credits).
Project report (PRO1; 3 university credits).

Opportunity to complete the requirements via supplementary examination

No information inserted

Opportunity to raise an approved grade via renewed examination

No information inserted

Examiner

Anders Lansner

Course web

No information inserted

Offered by

CSC/Computer Science

Main field of study *

No information inserted

Education cycle *

Second cycle

Add-on studies

No information inserted

Contact

Anders Lansner e-post: ala@nada.kth.se

Ethical approach *

• All members of a group are responsible for the group's work.
• In any assessment, every student shall honestly disclose any help received and sources used.
• In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.