Computer Engineering MA, Embedded Edge Intelligence, 3 credits

Versions:

Syllabus:
Datateknik AV, Inbyggd intelligens, 3 hp
Computer Engineering MA, Embedded Edge Intelligence, 3 credits

General data

  • Code: DT041A
  • Subject/Main field: Computer Engineering
  • Cycle: Second cycle
  • Credits: 3
  • Progressive specialization: A1N - Second cycle, has only first-cycle course/s as entry requirements
  • Education area: Technology 100%
  • Answerable department: Computer and Electrical Engineering
  • Approved: 2025-03-05
  • Version valid from: 2024-09-02

Aim

This course provides participants with the foundational theoretical and applied knowledge needed to understand and design edge intelligence systems, focusing on specific design challenges and practical solutions. The goal of the course is to introduce students to essential concepts in edge intelligence. Participants will learn about edge computing, cloud computing, embedded systems, real-time operating systems, and communication protocols for edge devices. The course covers TinyML, focusing on basic models, algorithms, and optimization for resource-constrained devices, along with training and deployment. Security, privacy, and ethical considerations in edge intelligence will also be addressed. The course concludes with an overview of current trends and practical research opportunities in the field.

Course objectives

Upon completion of the course, the student should be able to:

  • Architect edge intelligence systems tailored to various application setups.
  • Optimize the AI/ML models for resource-constrained devices.
  • Conduct a trade-off analysis between performance and resources.
  • Analyze the distributed learning, security, privacy, and ethical considerations in edge intelligence.
  • Determine suitable protocols and hardware.
  • Prototype edge intelligence systems using commercial components.
  • Evaluate the performance of edge intelligence.

Content

  • Challenges for edge intelligence systems
  • Hardware platforms for edge computing and edge intelligence
  • Real-time operating systems for edge intelligence
  • Network and Communication protocols for edge devices
  • AI/ML/TinyML models, algorithms, and architectures
  • Model optimization, training, deploying for resource-constrained devices.
  • Distributed Learning on Resource-constrained devices
  • Cloud integration and edge-cloud collaboration
  • Security, Privacy, and Ethical Considerations

Entry requirements

90 credits finished courses, with at least 60 credits in Computer Engineering BA (ABC), including 12 credits programming and 6 credits computer networks.

Selection rules and procedures

The selection process is in accordance with the Higher Education Ordinance and the local order of admission.

Teaching form

The course consists of lectures, reading assignments, projects, oral presentations, and a written exam.

The course may also be given as a self-study course.

Examination form

P101: Project Assignment, 1 Credits
Grade scale: Two-grade scale

T101: Written exam, 2 Credits
Grade scale: Seven-grade scale, A-F o Fx

Link to grading criteria: https://www.miun.se/gradingcriteria.


The examiner has the right to offer alternative examination arrangements to students who have been granted the right to special support by Mid Sweden University’s disabilities adviser.


Examination restrictions

Students are entitled to three examination opportunities within one year according to the examination format given in this version of the course syllabus. After the one-year period, the examination format given in the most recent version of the course syllabus applies.

Grading system

Seven-grade scale, A-F o Fx

{ value = Computer Engineering MA, Embedded Edge Intelligence, 3 credits }

:

The page was updated 10/14/2024