CloseHelpPrint
Kies de Nederlandse taal
Course module: 202200159
202200159
Embedded Artificial Intelligence
Course info
Course module202200159
Credits (ECTS)5
Course typeCourse
Language of instructionEnglish
Contact personprof.dr.ir. A.B.J. Kokkeler
E-maila.b.j.kokkeler@utwente.nl
Lecturer(s)
PreviousNext 1
Examiner
dr.ir. N. Alachiotis
Contactperson for the course
prof.dr.ir. A.B.J. Kokkeler
Examiner
prof.dr.ir. A.B.J. Kokkeler
Examiner
dr. D.V. Le Viet Duc
Examiner
dr. C.G. Zeinstra
Academic year2022
Starting block
2A
Application procedureYou apply via OSIRIS Student
Registration using OSIRISYes
Aims
After successfully passing the Embedded AI course, a student can:
  • explain basic ML/AI algorithms
  • construct ML/AI algorithms using basic building blocks
  • analyse functional and non-functional requirements of AI applications and based on that, select the most suitable embedded processing platform
  • implement (building blocks of) ML/AI algorithms onto embedded processing platforms
  • analyse the effects of implementation on the performance of the algorithm
  • assess the overall quality of the implementation (link between algorithm and implementation)
Content
In general terms, the Embedded AI course consists of the following topics:
  • Basics of machine learning and inference
  • Elementary building blocks of AI/ML algorithms
  • Non-standard computing- and resource-bounded (time, space, power) platforms for Embedded AI (microcontrollers, FPGA’s) Communication and sensing
  • Mapping of algorithmic building blocks onto computing platforms.
Applications (computer vision, natural language processing, localization, health monitoring)

Assessment
  • Test on the contents taught during the lectures (50%).
'< 10 students' => oral examination
'> 10 students' => written examination
  • Presentation and demonstration of project results + Written report (50%)
Project groups of 3-5 students, depending on the number of participating students.  
Assumed previous knowledge
- Basic programming skills
- Basic skills concerning programming hardware using a hardware description language
- Mathematics at (EE, CS, AT, AM, AP) bachelor's level
Participating study
Master Embedded Systems
Participating study
Master Electrical Engineering
Participating study
Master Computer Science
Required materials
Book
Efficient Processing of Deep Neural Networks, Vivienne Sze, Yu-Hsin Chen, Tien-Ju Yang, Joel Emer, Morgan & Claypool Publishers. ISBN 9781681738314
Recommended materials
-
Instructional modes
Lecture

Presentation(s)
Presence dutyYes

Project unsupervised
Presence dutyYes

Tests
Written/Oral Exam, Presentation, Project Report

CloseHelpPrint
Kies de Nederlandse taal