Learning Machines

Doel vak

1. Understanding and being able to critically discuss how learning machines relates to machine learning: This includes the main aspects involved in both, as well as their implications. (Knowledge and Understanding)
2. Designing systems of robots able to adapt to solve tasks: This includes endowing a robot with learning mechanisms that make use of sensing capabilities. (Applying Knowledge and Understanding)
3. Designing and conducting experiments with simulated and real robots to solve tasks. (Applying Knowledge and Understanding)
4. Being able to analyze the results from experiments (3), deriving insights into diverse aspects related to the methodology utilized. (Judgement)

Inhoud vak

• This course concerns designing robot systems that can sense their environment, act upon it, and improve their behavior to solve tasks.
• Previous years' assignment, to illustrate what the course involves: video
• Multiple tasks/assignments should be delivered, and students have the freedom to choose different learning and optimization methods to work with.
• Students are expected to apply algorithms to optimize the controllers (brains) of the robots to solve the given tasks while utilizing the sensors as inputs.
• All tasks will be done in simulation and in hardware using Robobo robots: these are wheeled robots with fixed bodies that possess infrared sensors and a camera.
• For the simulations, a robot programming/simulation framework will be provided to students (Coppelia).
• It is possible in a given year/period that both the robot platform and its simulator may diverge from Robobos, with additional optimization of the robot’s morphology/body.
• Most of the course encompasses practical sessions with only a few lectures.

Aanvullende informatie onderwijsvormen

• The course is short and requires intensive work - it happens over a period of four weeks - each week contains one lecture (Mondays), two practical sessions (Tuesdays or Wednesdays), and one presentation & evaluation session (Fridays). The complete schedule of each period will be made available on Canvas.
• Attendance at all sessions is mandatory. Missing any sessions must be justified to the teacher and might be very detrimental to the assignment of the week, while missing a presentation incurs failing the assignment of that week (unless a resit is taken).
• Students will work in teams.
• This is a course for students willing to go the extra mile, requiring a high level of independence.

Toetsvorm

• Task 0 - presentation: 0 points (formative assessment)
• Task I - presentation (group component): 1.5/10
• Task I - presentation (individual component): 0.5/10
• Task II - presentation (group component): 1.5/10
• Task II - presentation (individual component): 0.5/10
• Task III - presentation (group component): 1.5/10
• Task III - presentation (individual component): 0.5/10
• Final report - presenting results of all tasks: 4/10

For a student to pass the course, the grade of each task (both group and independent grades) and the grade of the report must be above 55% of their maximum. Task 0 must be delivered despite not being worth points.

The individual grade component will be evaluated during the presentations, per task:

• Every student must present part of the content (if the student is absent, a resit must be taken).
• The student should demonstrate individual/personal knowledge about how they solved the task.

If a student misses a presentation, they have the right to a resit by presenting another day.

Aanvullende informatie doelgroep

Master Artificial Intelligence
Master Business Analytics

Overige informatie

Use of generative AI is permitted, with explanation and reflection

In this course, generative AI (GenAI), such as ChatGPT or similar tools, may be used as part of the working process. The student must explicitly explain how GenAI was used and critically reflect on the quality, usefulness, and limitations of the output. Assessment also focuses on how GenAI has been used consciously, critically, and responsibly. Incorrect use of GenAI, including failure to comply with the requirements for explanation and reflection, is considered fraud. If established, the submitted work or assessment result will be declared invalid, and the Examination Board may impose further measures.

Toelichting Canvas

The complete schedule will be made available on Canvas, complementary to Rooster info.

Aanbevolen voorkennis

• Having passed any course involving learning/optimization algorithms, e.g., Reinforcement Learning, Evolutionary Computing, Computational Intelligence, Deep Learning, etc. The course will not teach you new algorithms, and therefore, it is fundamental that you have intermediate skills with at least one learning/optimization algorithm.
• Intermediate programming skills
• Python
• Independence for self-study.
• Experience with robotics simulators - these can be challenging to work with. (not as critical as items above)