Deep Learning is one key element of modern data science. This course will explore several instances of Deep Neural Networks, each one being specifically adapted to solve a particular learning task (classification, image recognition, text mining, dimensionality reduction). An introduction to current research topics on neural network will be presented during the last part of the course.
- Profesor: Latouche Pierre
- Profesor: Le Morvan Marine
- Profesor: Simsekli Umut
This course aims in providing the background for understanding the properties of low dimensional materials. It will address structure/property relationships with direct link to real systems and elaboration issues. Focus will be made on the main parameters governing the properties of these systems such as those related to size, morphology, surface state and spatial organization. The course also aims in providing numerous examples of practical issues taken from academic research or industrial applications.
- Surfaces and interfaces :
- substrates : chemical structure and preparation
- chemical modification of surfaces
- SAM – Self assembled monolayers
- Nanocrystals
- Basic properties and applications of nanocrystals
- elaboration issues (including nano-heterostructures)
- shape control and impact on properties
- materials from nanocrystals
- self organization of nanocrystals : supracrystals and mineral liquid crystals
- 2D materials materials
- General overview of layered materials
- Physical chemistry of graphene and derivatives
- 2D chalcogenides
- MX-ènes preparation and properties
- manipulation of 2D materials, assembly into heterostructures
- Functionnal hybrid organic/inorganic coatings
- liquid route deposition processes
- speciality polymers
- sol-gel chemistry of hybrid organic/inorganic compounds
- patterning : chemistry of conventional and soft lithography
- Nanostructured coatings from low dimensional nano-objects
This course aims in being understandable by any student having a very basic background in solid state physics and a very slight background or some curiosity in materials chemistry.
- Profesor: Delacroix Simon
- Profesor: Gacoin Thierry
- Profesor: Pierangelo Angelo
- Profesor: Schanne-Klein Marie-Claire
Objectifs du cours :
- Introduction to the concept of data stream processing
- Learning the basics on and how to use Data Stream Management Systems (DSMS)
- Understanding the main sampling techniques used for stream processing : sampling, sketching, etc.
- Understanding and using the main data stream processing algorithms
Syllabus :
This course deals with the algorithms and softwares commonly used to process large data streams. It aims at understanding the main difficulties and specificities of this type of data, knowing what different types of streams exist, what are the theoretical models and practical algorithms to analyze them, and what are the right tools to process these streams.
After an introduction of what data streams are from a conceptual point of view, this class covers the question of data stream processing from two different angles:
- A Machine Learning and Data Mining approach to cover the theoretical and algorithmic difficulties of learning from data streams: online learning vs incremental and batch learning, and sampling techniques.
- A more practical approach with an introduction to the various systems and software that are used to handle these data.
In terms of organization, the course will consist of an alternance of lectures and practical sessions. Finally, during the last class the students will have to present a recent research article of their choice on the subject of data stream processing.
Prérequis :
- Basics in SQL language
- Basics in Machine Learning (supervised and unsupervised)
- A knowledge of Java programming is recommended but not mandatory
Évaluation :
- The practical sessions will make ⅔ of the mark
- The research paper presentation will make ⅓ of the mark
- Profesor: Barry Mariam
- Profesor: Diao Yanlei
- Profesor: Sublime Jeremie
- Profesor: Togbe Maurras
Reinforcement learning aims at finding at each step of a process the best action to take in order to minimize some regret function. This course will introduce the general notions of reinforcement learning and will present several online algorithms that can be used in real-time to take actions. The specificity and the performance of the different algorithms will be discussed in detail.
Understanding and use the spatialization in LCA II
The aim of Life Cycle Assessment (LCA) course option is to describe why and how the spatialization can be useful and used in LCA. It provides the fundamental notions required to perform spatialized LCA, to use spatialization tools and to interpret and use spatialized LCA results in decision-making process. Students will have to carry out a specific question concerning spatialization in LCA.
Teaching staff
- Lynda Aissani, Research Engineer, INRAE
- Pierre Thiriet, Research Engineer, INRAE
- Samuel Le Féon, Research Engineer, INRAE
Course outline
- Why spatialize LCA?
- Exploring the need to spatialise and contextualise LCA using a small case study
- Based on a case study
- With some theoretical elements
- Bringing to light the problem of implementing the spatialisation of LCA
- How to spatialize?
- Work on 4 issues to be resolved (geographical grid, indicators, data required and tools required)
- With some theoretical elements for each of the 4 issues
- Work in groups to solve them at the end of the day
- Making progress on resolving the problem of implementing the spatialization of LCA
- With which tools?
- Based on the 4 points resolved in the previous lesson, implement the method using tools based on a combination of theory and practice.
- Work in groups to solve a question on the spatialization of LCA
- Understand the contribution of tools (R, possibly QGIS) to operationalise the resolution of the problem and be able to draw on the methodological lessons of the course
- Oral presentation of case study resolution
- Students present the solution for their question concerning spatialization
The module includes 10 hours of courses and 10 hours of practical work.
--------------------------------------------
Level required: Basic knowledge of LCA
Language: English
Credits ECTS: 3
Supervisor: Lynda Aissani
- Profesor: Aissani Lynda