Table of Contents
Machine Learning (48h, 6 ECTS)In charge: Michèle Sebag (CNRS, LRI - U. Paris-Sud). Lecturers
LanguageThe lectures will be given in French unless attended by non French-speaking students. Slides are in English. Motivations and main objectivesWe don't know how to write the specifications of an algorithm able to achieve face recognition or machine translation (I mean, a competent algorithm). In such domains, an alternative is to provide examples (this is a face, this is not a face) and to let the machine itself build the algorithm able to recognize faces (called, classifier): this is machine learning. Short descriptionThe lecture is structured as follows:
Lecture 1: Building intelligent machinesAfter Turing, machine learning was at the core of intelligent machines (one could carry through the organization of an intelligent machine with only two interfering inputs, one for pleasure or reward, and the other for pain or punishment.) But Artificial Intelligence took another direction. Why, what, etc. Lecture 2: Introduction to Supervised Machine LearningNotations and formal background. Oldies but goodies: Decision trees. Lecture 3: How to assess a machine learning algorithm
Lecture 4: Neural netsNN were at the beginning of ML, with excellent empirical results. Lecture 5: Support Vector MachinesSVM outpassed NNs, with a strong statistical theory and efficient algorithms (nothing practical like a good theory). Lecture 6: Come back of Neural netsDeep learning and applications. Lecture 7: Ensemble learningFrom finding the best classifier, to finding an ensemble of them. Lecture 8: ClusteringFinding clusters in the data; exploratory analysis. Application: you are given the catalog of a music editor. How to put some order in there ? Lecture 9: Data streamingModelling online data: e.g. electric consumption, job queries in a computational grid. The data are huge, their distribution is (usually) non stationary. Lecture 10: Metric learningAs usual, the problem is more than half solved if the representation/the metric is OK. Lecture 11: Reinforcement learningIf time permits. The goal is to learn a good policy: how to (learn to) play games, to program a robotic controller. ExamsThe exam involves two written essays (un partiel et un examen final). The questions will be in French (or in English if there are non-French speaking students). Students may answer in French or in English. Additionally, some focused issues (with an available tutorial) will be proposed: students can volunteer to present the issue to all other students for 30mns during the lecture time. Prerequisites
Related coursesBibliography
|