1. Computing with neurons
2. Learning in neural systems
3. Event-based sensing and computing
4. Neuromorphic hardware
5. Neuromorphic robotics
FDD3558 Solving Engineering Problems with Neural-inspired Computation 5.0 credits
The course presents neuromorphic engineering as a novel approach to computational systems that draw inspiration from nervous systems to process information in space and time. We will provide the students with the theoretical background necessary to implement spatio-temporal computation in neurons, and immediately apply that insight in practice. Concretely, we (1) discuss computational models and learning in decentralized and parallel neural systems, (2) present state-of-the-art neuromorphic software and hardware platforms, and (3) introduce neuromorphic sensors and robots. The course will conclude with a substantial individually designed project for all students.
Information per course offering
Information for Spring 2024 Start 18 Mar 2024 programme students
- Course location
KTH Campus
- Duration
- 18 Mar 2024 - 3 Jun 2024
- Periods
- P4 (5.0 hp)
- Pace of study
25%
- Application code
61027
- Form of study
Normal Daytime
- Language of instruction
English
- Course memo
- Course memo is not published
- Number of places
Places are not limited
- Target group
- No information inserted
- Planned modular schedule
- [object Object]
- Schedule
- Schedule is not published
- Part of programme
- No information inserted
Contact
Course syllabus as PDF
Please note: all information from the Course syllabus is available on this page in an accessible format.
Course syllabus FDD3558 (Spring 2024–)Information for research students about course offerings
P4 – Start date March 19 and for the following 4 weeks (5 lectures)
Headings with content from the Course syllabus FDD3558 (Spring 2024–) are denoted with an asterisk ( )
Content and learning outcomes
Course disposition
Course contents
1. Computing with neurons
2. Learning in neural systems
3. Event-based sensing and computing
4. Neuromorphic hardware
5. Neuromorphic robotics
Intended learning outcomes
After completing the course, the student should be able to
(1) Describe computational models for leaky integrators and leaky integrate-and-fire neurons, as well as ways to represent and encode information with biophysical models.
(2) Account for adaptation and learning in neuromorphic neural networks, including supervised optimization using surrogate gradients and unsupervised methods, including e-prop and EventProp.
(3) Understand address-event representations and account for the operating principles of event-based cameras and actuators.
(4) Write and execute neuromorphic algorithms on dedicated neuromorphic hardware.
(5) Quantitatively and qualitatively analyze neuromorphic algorithms and account for differences between neuromorphic and non-neuromorphic algorithms.
(6) Solve sensor processing and sensorimotor problems with neuromorphic neural networks.
(7) Implement neuronal computation and machine learning as energy efficient / energy saving processes.
Literature and preparations
Specific prerequisites
Linear algebra (SF1604 or similar)
Machine learning (DD2421 or similar)
Artificial Neural Networks (DD2437 or similar, or self-study to compensate)
Recommended prerequisites
Linear algebra (SF1604 or similar)
Machine learning (DD2421 or similar)
Artificial Neural Networks (DD2437 or similar, or self-study to compensate)
Equipment
Neuromorphic computing and cloud-based services will be provided as needed for the course.
Literature
Current research papers will be provided for the five lecture sessions.
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
- PRO1 - Project, 4.0 credits, grading scale: P, F
- ÖVN1 - Exercise, 1.0 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.
Students perform lab exercises for the 5 different lecture topics. At least four of the five lecture exercises need to be completed.
Other requirements for final grade
Students design and implement a project in neuromoprhic computing after the lectures. The project will be graded P/F.
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
No information inserted