Project Collective Intelligence

Doel vak

The main objectives of this course are:
1) To understand the notion of collective intelligence and natural and
artificial systems, and the difference between modeling them at the
macroscopic versus the microscopic scale,
(Knowledge and understanding)
2) To gain insight into open research issues related to collective
intelligence and collective dynamics,
(Knowledge and understanding)
3) To learn the use of simulators to conduct empirical research in this
field. (Apply Knowledge and understanding) (Make judgements) (Lifelong
learning skills)

Inhoud vak

The whole is greater than the sum of its parts. Or isn't it?
This course is concerned with collective intelligence and collective
dynamics.
We will elaborate on the differences between modeling these systems at
the microscopic versus the macroscopic scale, discuss the philosophical
as well as the technical aspects of such modeling, and learn to conduct
experiments with virtual agents that interact in virtual worlds.
Collective Intelligence concepts will be also positioned and studied in
relationship with Artificial Life and Swarm Robotics.

Aanvullende informatie onderwijsvormen

The course combines literature study and moderated discussions with
experimental work in computer simulations. Students will work in small
groups.

Toetsvorm

Students will work in teams of three, four, or five (depending on total

student numbers).

They will subject to a compulsory evaluation every week that involves a

presentation and demonstration with simulation videos. Answering questions during the group presentation and discussion is part of the assessment

Grading is based on:

1) Quality of the presentation and degree of achievement of the task:

a. Flocking: the agents need to move together in a group and in a common direction.

This task is mainly meant as a formative training

for the simulation environment (0% of the final grade - only a formative

grade will be given, assessed at the end of Week 1)

b. Aggregation: the agents should aggregate all in one shelter among

those available in the environment. (20% of the final grade, assessed at

the end of Week 2)

c. Collective dynamics simulation: A collective

dynamics linked to a specific scenario will be given to students to

simulate and study. Examples of this from past editions of the course are:

covid spread simulation, prey/predator dynamics. This

task runs for the final two weeks of the course (40% of the final grade,

the first 20% assessed at the end of Week 3 and the other 20% at the end

of Week 4)

2) short report of the approach and experimental results (40% of the

final grade)

The resit options are the following. In case one of the evaluations

listed under point 1) is missed (b or a component of c), the students

have the chance to submit a video containing a presentation and a live

demo. In this case, the grade of the specific component (b, or a part of

c) will be capped to 55%

In case of late submission of the report, a penalty of 10% on the grade

of the report component will be applied for each 24 hours of delay. A

maximum of 5 days delay is allowed (corresponding to a penalty of 50% on

the grade of the report component).

Literatuur

Introductory papers on swarm robotics and collective dynamics, e.g. the
review here https://link.springer.com/article/10.1007/s11721-012-0075-2

Aanvullende informatie doelgroep

Bachelor Artificial Intelligence (Year 2)

Afwijkende intekenprocedure

Students take this course in groups. Creating groups sufficiently early
is of paramount importance given the tight schedule of the course.
Therefore, students are requested to check Canvas announcements up to
one week before the official start of the course, and execute any
instructions about group formation contained in the announcement.

Aanbevolen voorkennis

Coding skills in Pyhton are necessary.
Students are required to download, install, and use simulation software.
Students should also have the will to switch to a more research-oriented
mindset (the course is not about following instructions, but proposing
research problems and approaches to solve them, with a strong
motivation).