Duration
26h Th, 26h Pr
Number of credits
Lecturer
Language(s) of instruction
English language
Organisation and examination
Teaching in the first semester, review in January
Schedule
Units courses prerequisite and corequisite
Prerequisite or corequisite units are presented within each program
Learning unit contents
Format: 2 x (3 online lectures + 1 in person exam) + in-person final project
Online Lectures: One chapter of the book "The Cambridge Handbook of Computational Cognitive Sciences", Cambridge University Press, per lecture, possibly complemented by lecture notes and research papers. Format: Lecture will be run as a teacher-guided journal club presented by the students. The teacher will complement the presentation as needed.
N.B.: To prepare the presentations, the use of AI is not strictly forbidden but highly discouraged. It is highly unlikely you will be able to pass the course exams if you rely too much on AI.
Exams: 3-hour long, hand-written, guided essays over one of the topics covered during the previous lectures. No phones, laptops, earphones, and other kinds of smart devices will be allowed during the exams. Students caught cheating will be expelled from the lecture room and will receive a note of 0/20 in the exam. Questions to the teacher are of course allowed.
In-person final project: Development of a Python or Julia code implementing a student-chosen model from those studied during the course, with the help of the course teacher. AI-generated code is allowed for the final project.
The course will cover to main themes:
- Artificial vs Biological Neural Networks (including dynamical systems)
- Bayesian Inference as a model of cognition
Learning outcomes of the learning unit
Students will be able to understand and use the most important and most widely used models of cognition, and how this model could be used in their engineering practice.
The course is open to non-engineering students, with the goal of fostering as rich an interdiscplinary discussion as possible.
Prerequisite knowledge and skills
Python or Julia coding.
Linear algebra, analysis, and basic differential differential equations.
Planned learning activities and teaching methods
The course will largely be based on the book:
Sun R, ed. The Cambridge Handbook of Computational Cognitive Sciences. 2nd ed. Cambridge University Press; 2023.
plus research paper that will be distributed during the course.
The course will end with a final project guided by the professor.
Mode of delivery (face to face, distance learning, hybrid learning)
Blended learning
Further information:
The course will be given in hybrid format:
- Lectures will be in remote (Teams videocall) journal club formats
- Exams will be in-person.
During the (in person) first lecture, on September 16, the precise calendar of both remote and in-person lectures will be fixed.
Course materials and recommended or required readings
The course will be based on the monograph:
The Cambridge Handbook of Computational Cognitive Sciences, 2nd Edition, Ron Sun Ed., Cambridge University Press, 2023.
Exam(s) in session
Any session
- In-person
written exam AND oral exam
Written work / report
Further information:
Exams: 80%
Final project: 20%