Intelligent systems: communications & AI

COM-304 / 8 credits

Teacher(s): Al Hassanieh Haitham, Roshan Zamir Amir

Language: English

Withdrawal: It is not allowed to withdraw from this subject after the registration deadline.

Summary

The course teaches the development of systems that solve real-world challenges in communications, signal processing, foundation models, robotics, and AI. Students will work in teams, construct their ideas, and either program available hardware prototypes or build their hardware or software system.

Content

The course will teach students both technical and project management skills which are essential in developing, designing, and prototyping practical systems where the underlying challenges fall in on or multiple areas with a focus on communication, signal processing, and AI, in particular foundation models and robotics.

 

The primary goal of this course is to give students hands-on experience with solving real-world challenges by working in teams to program different hardware platforms and ultimately build their own projects. The overall structure of the course will consist of a introductory lectures at the beginning to introduce the project and research areas in wireless radar sensing, communication, computer vision, foundational models, and robotics. The students will have time to go through the background material needed for the course and get familiar with the hardware and sensor platforms. Students will then organize into groups of 3 or 4 and propose their project using one or more of the provided hardware platforms, with the aid of the course staff. Finally, students will design and build their own project.

 

This class has two types of lectures.

 

(1) In person lectures at the beginning of the semester. After which the lecture time will be used as office hours to help students with their projects.

 

  1. Lecture 1: Class Introduction
  2. Lecture 2: Introduction to Wireless Communications & Sensing
  3. Lecture 3: Introduction to Perceptual Robotics and Reinforcement Learning
  4. Lecture 4: Introduction to foundation models, transformers, and multimodal learning

(2)Online lectures on background material.

 

  1. Wireless Communication
  2. Radar Signal Processing
  3. Robotics and Reinforcement Learning

 

The class will support 3 hardware platforms which students can work with.

 

 

We have two additional robots which students can use. However, we do not provide support for these robots and we only have one available from each type.

 

 

Learning Prerequisites

Recommended courses

COM-102 Avanced Information, Computation, Communication II (BA2)

CS-202 Computer Systems (BA4)

COM-202 Signal Processing (BA4)

CS-Introduction to Machine Learning (BA4)

COM-302 Principles of Digital Communications (BA6) (To be taken concurrently)

Teaching methods

- lectures

- Tutorials on the hardware prototypes

- Continuous supervision and tutoring

- Extensive team work and team feedback

 

Expected student activities

  • Take an entrepreneurial approach to create and develop a practical system under the given hardware constraints.
  • Work with team members to complete a large practical project
  • Independently research solutions, learn new concepts and apply them in practice.
  • Debug software/hardware systems.
  • Discuss project progress in class
  • Provide constructive criticism and feedback to other groups
  • Present project outcome in a public forum

 

Assessment methods

Individual activites grade 35%

Team project grade 65%

Supervision

Office hours Yes
Assistants Yes
Forum Yes

In the programs

  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Intelligent systems: communications & AI
  • Courses: 2 Hour(s) per week x 14 weeks
  • Project: 10 Hour(s) per week x 14 weeks
  • Type: optional
  • Semester: Spring
  • Exam form: During the semester (summer session)
  • Subject examined: Intelligent systems: communications & AI
  • Courses: 2 Hour(s) per week x 14 weeks
  • Project: 10 Hour(s) per week x 14 weeks
  • Type: optional

Reference week

Related courses

Results from graphsearch.epfl.ch.