The course includes algorithms that obtain their computational properties based on training on examples. You therefore avoid to state rules explicitly but work via training on measured data. The learning can either be controlled by straight reply is given or be completely autonomous. The course also goes through principles of representation of data in neural networks. We bring up hardware architectures for neural calculations (neural chips and neural computes) and show how ANN is used in robotics. We also show technical applications of learning systems in problem areas as pattern recognition, combinatorial optimisation and diagnosis.
FDD3432 Graduate Course in Artificial Neural Networks and Other Learning Systems 6.0 credits
This course has been discontinued.
Last planned examination: Spring 2022
Decision to discontinue this course:
No information insertedInformation for research students about course offerings
For information please contact Erik Fransén
Course offerings are missing for current or upcoming semesters.
Headings with content from the Course syllabus FDD3432 (Spring 2019–) are denoted with an asterisk ( )
Content and learning outcomes
Course contents
Intended learning outcomes
After the course, the students should be able to
- explain the function of artificial neural networks (ANN) of the type Back-prop, Hopfield, RBF and SOM
- explain the difference between supervised and unsupervised learning
- account for assumptions and derivations behind the ANN algorithms that are brought up in the course
- give examples of design and implementation for small problems
- implement ANN algorithms to achieve signal processing, optimisation, classification as well as process modelling
in order to
- obtain an understanding of the technical potential as well as advantages and limitations of the learning and self-organizing systems of today
- in the working life be able to apply the methodology and produce implementations.
Literature and preparations
Specific prerequisites
No information inserted
Recommended prerequisites
No information inserted
Equipment
No information inserted
Literature
Fausett, Fundamentals of Neural Networks, Prentice Hall.
Examination and completion
If the course is discontinued, students may request to be examined during the following two academic years.
Grading scale
P, F
Examination
- EXA1 - Examination, 6.0 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.
In this course, the code of honor of the school is applied, see: http://www.kth.se/en/csc/utbildning/hederskodex
Opportunity to complete the requirements via supplementary examination
No information inserted
Opportunity to raise an approved grade via renewed examination
No information inserted
Examiner
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.
Further information
Course room in Canvas
Registered students find further information about the implementation of the course in the course room in Canvas. A link to the course room can be found under the tab Studies in the Personal menu at the start of the course.
Offered by
Main field of study
This course does not belong to any Main field of study.
Education cycle
Third cycle
Add-on studies
DD3431, DD3435
Contact
Erik Fransén, erikf@kth.se