Proposed by Groupe INSA member of Network "n+i"

Organized by: INSA TOULOUSE
Domains: OptimisationInformatics - Computer ScienceStatistics
Duration: 2 weeks
Available language:
Required french level: Aucun
Required english level: B1
Required level of studies: licence/bachelor
Nature of certification: ECTS

 INSA Toulouse, 135 avenue de Rangueil 31400 Toulouse

Training description

 The aim of this series of Lectures is to provide the basic background for dealing with Optimization issues in deterministic and stochastic environment.

More specifically, we address the main features of smooth optimization algorithms with and without constraints: in addition to the theoretical material, we describe deterministic and stochastic gradient algorithms, Newton-type algorithms, least square algorithms.

This part will be completed by an introduction to nonsmooth optimization algorithms (sub gradient algorithms and proximal algorithms).

All these optimization algorithms will be implemented during practice classes with application to image processing.

The second part of the Lectures will be devoted to actual Statistical issues related to Machine Learning.

Other programs:

  • Logo of

    Rendez-vous Aeronautics / Aerospace in Toulouse and Paris

    Discover the French know-how in Aeronautics & Aerospace Who is eligible? Students in engineering and technology, over 18 years old. 1 week

  • Logo of


    How about building your own drone? Make it happen at the IPSA Summer School 2022! We prepare a 3-week program in Paris dedicated to passionate studen

  • Logo of

    ESTP – EPF - AIvancity : Summer school “Artificial Intelligence for Sustainable Smart Cities”

    Summer School Artificial Intelligence for Sustainable Smart Cities Academic program A particular attention is dedicated to the following subjects:

  • Logo of

    Rendez-vous French Know how & Higher Education in Paris

    Discover the French know-how & higher education in sciences & technologies Objective The objective of this exceptional event is to host a se