Graduate School and Research Center In communication systems

Bernard MERIALDO

Bernard MERIALDO
Bernard MERIALDO
Eurecom - Data Science 
Professor
04 93 00 81 29
04 93 00 82 00
423

Teaching

  • In 1980-1981, he taught at the Faculty of Sciences in Rabat (Morocco).
  • Between 1992 and 2015 he was in the Multimedia Dept.
  • Now he teaches Intelligent Systems and Multimedia Information Retrieval in the Data Science Dept. 

My courses

  • MALIS / Fall 2016 - Machine Learning and Intelligent System

    The objective of this course is to give students a solid background in Machine Learning techniques. "Machine learning is a scientific/engineering discipline that deals with the construction and study of algorithms that can learn from data. Such algorithms operate by building a model based on inputs and using that to make predictions or decisions, rather than following only explicitly programmed instructions." (Wikipedia) These techniques are used to build efficient models for problems for which an optimal solution is unknown. For example, Deep Networks have recently shown impressive performance in pattern recognition tasks (vision, language, speech).

    This course will introduce the basic theories of Machine Learning, together with the most common families of classifiers and predictors. It will identify the basic ideas underlying the mechanism of learning, and will specify the practical problems that are encountered when applying these techniques, optimization, overfitting, validation, together with possible solutions to manage those difficulties.

     Duration : 42 hours, including 9 hours of practise

  • MMIR / Fall 2016 - Multimedia indexing and retrieval

    • While search engines such as Google are extremely efficient for huge databases of text documents, searching for image and video information is still a research challenge.
    • The objective of this course is to study some of the problems and techniques that are involved in the construction of multimedia search engines.