Objectives of Programme's Learning Outcomes

• Scientific skills
• Implement and independently carry out an experimental approach, validate a model by comparing its predications with experimental results, assess the limitations of the model's validity, and identify sources or error.
• Use acquisition and data analysis software specific to biomedical sciences
• Be familiar with biomedical science research tools, including bioinformatics tools.
• Appropriately select measuring instruments, analyse and process the signal obtained
• Use basic mathematical tools
• Be a responsible researcher: - Know how to base their reasoning on data obtained from scientific literature. - Know how to integrate an ethical dimension in their reasoning. - Be loyal (to the facts, to the team, and to intellectual property). - Do not tamper with results. - Do not exploit the work of others. - Demonstrate experimental rigor.
• Professional integration skills
• Demonstrate their ability to research, analyse and synthesise: - Research, analyse, use different sources of information and materials related to biomedical sciences, format them to draw up a summarised document, produced and broadcast them on digital media. - Carry out a study, identify and raise an issue in a predefined context, build and develop an argument, interpret the data and results, develop an overview, and propose extensions. - Question themselves, think critically, debate, and defend their ideas.
• Master written and oral scientific expression. Be independent in writing and show that they can communicate their thoughts, reason and organise their knowledge
• Master scientific English: - Present scientific results, orally and in writing. - Answer scientific questions in English

Learning Outcomes of UE

After successful completion of this course, the students will be able to:
 - Understand the basic principles of IA and BCI
 - Have a clear overview of the main classification algorithms and know when to (not) use them
 - Apply these algorithms to neurophysiological data
 - Avoid the main methodological pitfalls and biases by using better experimental designs

This course gives the students the necessary tools to understand and interact with Data Scientists/Engineers in their future work environment.

UE Content: description and pedagogical relevance

The course is articulated around 3 main parts:
 - Introduction to Artificial Intelligence (about 16 hours)
 - Introduction to Brain-Computer Interfaces (about 8 hours)
 - Project (about 6 hours)

The main objectives of this course are to:
 - Introduce the fundamental notions and principles of Artificial Intelligence (AI) and Brain-Computer Interfaces (BCI)
 - Apply these fundamental principles with state-of-the-art algorithms on neurophysiological data 
 - Identify and avoid methodological pitfalls and biases
 - Discuss recent research results related to the use of AI and BCI in Neuroscience

Prior Experience

No prerequisites are required for this course.