27250014 - Introduction to AI, Machine Learning & Knowledge Extraction

The course introduces the field of artificial intelligence, with a particular focus on machine learning implemented in knowledge extraction from data. 

Estimation of private study (outside of contact hours): 30 hours

TARGETED KNOWLEDGE AND SKILLS 

Mastering the whole knowledge discovery cycle and implement it using Python and interactive tools. 

COURSE OUTLINE

1. Introduction
2. Knowledge discovery from databases
3. Supervised Learning

• Basics of supervised learning
• Decision trees, random forests
• K-Nearest Neighbors (KNN)
• Support Vector Machine (SVM)
• Regression

4. Unsupervised learning

• clustering

5. Data Mining

• Association rules
• Formal concepts analysis

6. Deep Learning
7. Implementation

• Knime
• Python libraries : Numpy, Pandas, Matplotlib/Seaborn, scikit-learn, concepts

PRESCRIBED TEXTS AND PUBLICATIONS

• S. Russell, P. Norvig, Artificial Intelligence: A Modern Approach, 2003.

RECOMMENDED TEXTS AND PUBLICATIONS

• Rémi Gilleron, Apprentissage machine – Clé de l’intelligence artificielle – Une introduction pour non-spécialistes, Ellipses, 2019
• Antoine Cornuéjols, Laurent Miclet, Apprentissage artificiel : Concepts et algorithmes
• Virginie Mathivet, Machine Learning

TEXTS AND PUBLICATIONS OF IAELYON FACULTY ON THE SUBJECT OF THE COURSE  

1. Béatrice Fuchs, Jean Lieber, Laurent Miclet, Alain Mille, Amedeo Napoli, Henri Prade & Gilles Richard (2020). « Case-Based Reasoning, Analogy, and Interpolation ». A Guided Tour of Artificial Intelligence Research, Pierre Marquis, Odile Papini, Henri Prade, Springer International Publishing, pp. 307-339. doi : 10.1007/978-3-030-06164-7_10.
2. Béatrice Fuchs & Amélie Cordier (2018). « Interactive Interpretation of Serial Episodes: Experiments in Musical Analysis ». 21st International Conference on Knowledge Engineering and Knowledge Management (EKAW-2018), 16 novembre 2018, Nancy (France), pp. 131-146. doi : 10.1007/978-3-030-03667-6_9.
3. Béatrice Fuchs, Jean Lieber, Alain Mille & Amedeo Napoli (2014). « Differential adaptation: An operational approach to adaptation for solving numerical problems with CBR ». Knowledge-Based Systems, vol. 68, pp. 103-114. doi : 10.1016/j.knosys.2014.03.009. 

Individual grade
Oral presentations of projects, 15min

Other grade(s)
Projects to be submitted in the form of a report and a practical assignment

TEACHING METHODS
NATURE OF MATERIALS

Online course materials

PRE-REQUISITES IN TERMS OF KNOWLEDGE AND SKILLS

The basics of algorithms and programming
The basics of probability and statistics