Degrees incorporating this pedagocial element :
Description
This course aims to introduce to students the basics of and a large overview on Artifical Intelligence, including Machine Learning, Deep Learning and Symbolic AI.
Providing a solid background in AI, understanding the principles in AI, developping the skills to model, implement and deploy simple AI models in different contexts, analysing the advantage and the limits of AI
Syllabus
The course contains three parts. 1. Machine Learning: Basics, Supervised ML, Unsupervised ML, Regularization, Evaluation of ML. 2. Deep Learning: Dense neural networks, Convolution Neural Networks, Recurrent Neural Networks, Gradient Descent, Backpropagation, Large Language Model (it time permits). 3. Symbolic AI: Logic-based Knowledge, Rule-based Reasoning.
Recommended prerequisite
Very basic notions in Linear Algebra (Matrices), Analysis and Probability, basic programming in Python
Targeted skills
Understanding the notions and principles, manipulating simple analysis, implementing AI models
Bibliography
An introduction to Statistical Learning, very good book with online version: https://www.statlearning.com/
In brief
Credits : 3Number of hours
- Lectures (CM) : 19.5h
- Practical work (TP) : 13.5h
Language(s) : English
Contact(s)
Kim Thang Nguyen
Sylvain Bouveret