Differences

This shows you the differences between two versions of the page.

--- teaching:mfe:ia [2015/03/26 14:28]
bersini [Expérimentation des designs patterns pour la modélisation de systèmes biologiques complexes]
+++ teaching:mfe:ia [2016/03/14 16:03]
mdorigo [Localisation and tracking of components in self-assembling systems]
@@ Line 1: / Line 1: @@
-====== MFE 2013-2014 : Intelligence Artificielle ======
+====== MFE 2015-2016 : Intelligence Artificielle ======
 ===== Introduction =====
@@ Line 11: / Line 11: @@
 Ce mémoire se fera en collaboration avec l'équipe médicale du centre pour l'anorexie et la boulimie de l'hôpital Erasme. Il consistera en l'analyse informatisée des données récoltées lors d'entretiens avec le patient et sa famille au cours du traitement. Les données sont actuellement stockées dans dans une base de données SPSS.  Le mémoire consistera pour l'essentiel au traitement de ces données par des approches "Machine Learning" et "Data Mining" dans une perspective de Quality Management.
+  * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
+===== Développer un programme informatique permettant une analyse statistique en vue de  l'évaluation d'un module psychothérapeutique. =====
+Ce mémoire se fera en collaboration avec l'équipe médicale du centre pour l'anorexie et la boulimie de l'hôpital Erasme. Il consistera en l'analyse informatisée des données récoltées lors d'entretiens avec le patient et sa famille au cours du traitement. Les données sont actuellement stockées dans dans une base de données SPSS.  Le mémoire consistera pour l'essentiel au traitement de ces données par des approches "Machine Learning" et "Data Mining" dans une perspective de Quality Management.
+  * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
+===== Contribution au développement de la plateforme Big Data d'IRIDIA =====
+Dans de nombreux projets d'enseignement et d'industrie dans lesquels IRIDIA se trouvent impliqués, des demandes pressantes nous sont faites de formation et d'utilisation des outils Big Data (Map-Reduce, Cloudera, Hue, Hive, Pig, Elastic Search, HBase). Nous répondons tant bien que mal à ces demandes et tentons d'équiper notre cluster avec les logiciels demandés. Le mémoire consisterait en une étude comparative de l'existant en terme surtout logiciel et la mise en place d'un cours mettant en évidence les avantages de l'une ou l'autre solution en ce compris par rapport à des solutions plus conventionnels de type BD relationnelle.
   * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
@@ Line 24: / Line 36: @@
 Depuis quelques années, Microsoft met en avant un nouveau langage de programmation F# créé dans le sillage des langages dits déclaratifs ou fonctionnels. Il semblerait que ce langage soit idéal pour le traitement des données. Le MFE consistera en une étude expérimentale de ce langage et un comparatif avec les langages de programmation aujourd'hui les plus usités.
+ * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
+===== Etude de l'algorithme du Deep Learning =====
+Les réseaux de neurones multicouches sont redevenus très à la mode depuis que Google les utilise massivement pour le traitement automatique d'images et de vidéos. Nous avons à IRIDIA étudié et réalisé plusieurs algorithmes d'apprentissage de ces réseaux multicouches. Le mémoire consistera en une comparaison des algorithmes de deep learning tels ceux utilisés chez Google et les alternatives que nous proposons ici à IRIDIA depuis plusieurs années.
  * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
@@ Line 102: / Line 120: @@
   * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
@@ Line 110: / Line 129: @@
   * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
-===== Mise au point d’un système automatique de génération d'équations différentielles au départ d’un diagramme d’état-transition =====
+===== Mise en place de solutions Big Data et Elastic Search pour les réseaux bibliométriques  =====
+Les publications scientifiques doivent se citer entres elles. Elles constituent donc un immense réseau de citations. Nous étudions à IRIDIA la nature de ce réseau et l'impact que peut avoit une publication scientifique en suivant dans le temps le nombre de nouvelles publications qui citent cette dernière. Comme ces réseaux sont de taille gigantesque (des millions de publications), des solutions technologiques harwarde et software de type Big Data et Elastic Search sont mises en place et expérimentées ici à IRIDIA. Le mémoire consistera en un développement et une expérimentation des ces possibles solutions.
+* Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
-Le diagramme d’état-transition représente le cycle de vie d’un objet, de sa naissance à sa disparition, en suivant les différents états par lesquels cet objet transite. Lorsqu'il s'agit d'objets biologiques, il est possible de ré-interpréter ce diagramme comme la transition d'une
-partie d'une population d'objets dans un certain d'état dans l'état qui
-suit. Dans ce cas, ce diagramme peut se traduire sous forme d'un système
-d'équations différentielles que l'on devra pouvoir générer automatiquement.
-  * Contact : [[http://code.ulb.ac.be/iridia.people.php?id=1|Hugues Bersini (IRIDIA)]]
-  *
 ===== Mise au point d’un langage de modélisation de systèmes biologiques inspiré des diagrammes de classe et d'état/transition UML =====
@@ Line 160: / Line 177: @@
     * [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo (IRIDIA)]]
     * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~mbiro|Mauro Birattari (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
-===== Optimising Ant Colony Algorithms for Performance ======
-Ants have inspired a number of computational techniques and among the most successful is ant colony optimization (ACO). ACO is an optimization technique that can be applied to tackle a wide variety of computational problems that arise in computer science, telecommunications, and engineering.
-The goal of this project is to improve the performance of ACO algorithms by investigating and testing various implementation techniques: intrinsic functions (MMX/SSE floating-point operations), CPU cache effects, or GPU programming.
-Required skills: knowledge of C programming. Some knowledge about computer architecture.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~mbiro|Mauro Birattari (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
-===== Graphical Tools for analysing Multi-Objective Data. =====
-In multi-objective problems, not only one objective function must be minimised but several, often conflicting, objectives must be taken into account. The result is often a set of solutions modelling the trade-off between the objectives of the problem.
-The goal of this project is to develop graphical tools to interactively examine and compare the results of algorithms for multi-objective problems.
-Required skills: The candidate should be well acquainted with programming in object oriented languages.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
@@ Line 212: / Line 198: @@
     * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
     * [[http://iridia.ulb.ac.be/~mbiro|Mauro Birattari (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
+    * [[http://iridia.ulb.ac.be/~lperez|Leslie Perez (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~jdubois|Jérémie Dubois-Lacoste (IRIDIA)]]
-===== Stochastic Local Search heuristics for solving NP-complete puzzles. ======
-This project is about single player games (puzzles) and the design of algorithms for tackling hard combinatorial optimisation problems.
-Example puzzles are: [[http://en.wikipedia.org/wiki/Light_Up|Light Up]], [[http://en.wikipedia.org/wiki/Mastermind_(board_game)|Mastermind]], [[http://en.wikipedia.org/wiki/Minesweeper_(video_game)|Minesweeper]], etc.
-The student will learn how to design and implement a Stochastic Local Search algorithm to solve NP-complete puzzles. The student will also learn how to analyse the performaces of the algorithm and perform statistically sound comparisons with the other algorithms available in literature.
-Required skills: good knowledge of C or C++ programming.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~fmascia|Franco Mascia (IRIDIA)]]
-===== Analysis of Local Optima Networks for the Max-Clique problem. ======
-Stochastic Local Search algorithms search for optimal solutions in a large space of candidate solutions. Local Optima Networks (LON) are representations of search landscapes of combinatorial optimisation problems. In these networks, nodes are local optima of the problem, and edges are weighted transitions between the optima. These networks model in a more compact way the properties of the larger search spaces they represent.
-The goal of this project is to build LON of small instances of the Maximum Clique (MC) problem, and measure properties that could illustrate the differences between instance families.
-The MC problem is an NP-hard combinatorial optimisation problem that asks to find the biggest completely connected component of a graph. It has relevant applications in information retrieval, computer vision, social network analysis, computational biochemistry, bioinformatics and genomics.
-Required skills: good knowledge of C or C++ programming.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~fmascia|Franco Mascia (IRIDIA)]]
@@ Line 262: / Line 216: @@
   * Contacts :
     * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~fmascia|Franco Mascia (IRIDIA)]]
+    * [[http://code.ulb.ac.be/iridia.people.php?id=1393|Alberto Franzin (IRIDIA)]]
@@ Line 309: / Line 263: @@
-===== Collective Decision Making with Heterogeneous Agents =====
-Swarm robotics is an interesting approach to the coordination of hundreds of robots as it promotes the realization of systems which are scalable, robust and flexible.
-The master thesis will study how to provide a swarm system with the cognitive capability of collective decision making.
-Each agent has partial knowledge of the available alternatives and of their quality estimate, however the swarm, as a whole, is able to decide for the best option. Recently, numerous works have studied strategies and algorithms to implement this process in distributed systems (often taking inspiration from biology, e.g., bees or cockroaches behaviour). One of the common characteristic of these works is that all the agents of the swarm has the same behaviour. In the Master Thesis project, the student will study how heterogeneity influences the global outcome. We will consider heterogeneity both in the individual behaviour (for instance, robots can estimate diﬀerent option characteristics) and in the interaction network.
-In practice, the student is supposed to (i) model the collective decision making problem
-(ii) design and implement multi-agents simulations, and (iii) analyse and discuss the obtained
-results. Depending on the student skills and preferences, the work can focus more on theoretical
-aspects, thus favouring the modelling and analysis of the problem, or can be more practical,
-thus centring the thesis on the multi-agent implementation part. Possibly, a more practical
-thesis could result (depending on the student skills) in the implementation of a real world
-demonstrator with a swarm of up to 100 robots.
-* Contacts : [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] and Andreagiovanni Reina (IRIDIA)
@@ Line 427: / Line 365: @@
-===== Automatic fitness function definition in evolutionary robotics =====
+===== Swarm construction: development of remote monitoring software for intelligent structures =====
-Evolutionary robotics is a fascinating approach to the design of robot controllers that takes inspiration from natural evolution.
+S-blocks are dynamically reconfigurable blocks used for swarm-based autonomous construction applications. When two or more S-blocks are assembled they are capable of communicating with each other over a near field communication (NFC) wireless interface. The goal of this master thesis is to develop software to monitor (and control) the blocks in an intelligent structure remotely over the auxiliary Zigbee-based wireless interface. As only one block in the structure is fitted with this wireless interface, it is required that the other blocks communicate with the PC, via routing messages through the block-to-block NFC interfaces. This will require the software on the S-Blocks to be enhanced to use preemptive task swapping, to allow multiple blocks to communicate with each other simultaneously.
-In order to obtain a robot that is able to perform a desired task, the evolutionary robotics approach considers a population of robots that evolves in time. Each robot is characterized by a genotype that defines somehow its behavior. Each robot is evaluated according to a fitness function that measures the ability of the robot to perform the desired task. Robots with a low fitness are eliminated. Robots with a high fitness remain in the population and generate offsprings -- e.g., robots with a similar genotype obtained via mutation and/or cross-over. Through this process, generation by generation, the evolutionary robotics approach is able to obtain robots that present higher and higher fitness and that are therefore able to perform the desired task more and more effectively.
+Required skills: The candidates should understand low level computer concepts such as: interrupts, timers, and registers, have some experience with C/C++ programming, and have a working knowledge of the English language.
-One of the main open problems in evolutionary robotics is that the definition of an appropriate fitness function is a very complex, labor-intensive, and time-consuming activity that requires the attention of an expert researcher.
-The goal of this master thesis is to devise an automatic method to define a fitness function in order to obtain a robot that is able to perform a desired task. This automatic method will be based on machine learning and metaheuristic algorithms. In particular, it will draw ideas from the fields of reinforcement learning and of on-line adaptation of parameters in optimization algorithms.
-Required skills: The candidates should be acquainted with C/C++ programming and have a working knowledge of the English language.
-* Contact: [[http://iridia.ulb.ac.be/~mbiro|Mauro Birattari]], Marco Dorigo, Vito Trianni (IRIDIA)
+* Contact: [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] (IRIDIA)
-===== Evolution of Modular Controllers for Simulated and Real Robots =====
-The goal of this master thesis is investigating how modularity in a robot controller can influence the quality of the behaviours obtained through artificial evolution.
-Similarly to the nervous system that can be divided in central and peripheral, the project will study a modular architecture for neural network controllers. The peripheral modules encode the information coming from the sensory subsytems or going to the motor apparatus. The central system encodes the behavioural rules that map sensations to actions. The project will study methods to develop the peripheral modules by maximising the information transfer from the sensory input and to the motor output, on the basis of measures derived from Information Theory.
-The project will involve experimental activities with both simulated and real robots, and will investigate both individual and collective behaviours.
-Required skills: The candidates should be acquainted with C/C++ programming and have a working knowledge of the English language.
-* Contact: [[http://iridia.ulb.ac.be/~vtrianni|Vito Trianni]], Marco Dorigo (IRIDIA)
+===== Design of a holonomic drive system for autonomous robots in a swarm =====
-===== Localisation and tracking of components in self-assembling systems =====
+Unlike a differential drive system, a holonomic drive system has the advantage of being able to move in any direction at a given instant. The goal of this master thesis is to design and evaluate the performance of a holonomic drive system. The drive system will be assembled from a combination of off-the-shelf components and 3D printed parts. In order to evaluate the drive system, close loop controllers need to be designed and evaluated in C/C++.
-The goal of this project is to apply computer vision techniques to track the growth of structures in self-assembling systems. The ability to track the growth of structures will shed light on the dynamics of self-assembly; an aspect of self-assembly that has not been well researched in the macroscopic context.
+Required skills: The candidates should have some experience with programming in C/C++, and some experience with 3D modelling (preferably Solidworks). The candidates should be able to use basic kinematics to solve simple physics problems, and have a working knowledge of the English language.
-As part of the project, the student will have to: (a) find suitable hardware (combination of camera, lens, lighting, etc.), (b) localise multiple components in an environment, (c) track the components in the environment, and (d) track the assembly of components in the environment.
+* Contact: [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo]] (IRIDIA)
-Required skills: the candidates should be able to program in C++ and have a working knowledge of the English language.
- * Contacts : [[http://iridia.ulb.ac.be/~mdorigo/HomePageDorigo/ | Marco Dorigo]] and Dhananjay Ipparthi (IRIDIA)
@@ Line 543: / Line 464: @@
-===== Applications of the Multi-objective ACO framework =====
+===== Applications of a hybrid SLS algorithm framework =====
-We have recently developed a software framework of Ant Colony Optimization algorithms for multi-objective optimization problems. This framework has only been applied to a few problems. The goal of this project would be to extend this framework to other problems and compare its results with the methods proposed in the literature. The student will learn to solve multi-objective optimization problems with ACO algorithms, automatic configuration of optimization algorithms, and analysis and comparison of optimization algorithms for multi-objective problems.
+We have recently developed a software framework from which hybrid stochastic local search algorithms can be designed automatically. This framework has only been applied to a few problems. The goal of this project would be to extend this framework to other problems and compare its results with the methods proposed in the literature. The student will learn to solve combinatorial optimization problems with SLS algorithms, automatic configuration of optimization algorithms, and analysis and comparison of optimization algorithms.
   * Contacts :
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
     * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~mdorigo|Marco Dorigo (IRIDIA)]]
+    * [[http://code.ulb.ac.be/iridia.people.php?id=1388|Federico Pagnozzi (IRIDIA)]]
-===== A graphical interface for the optimisation of Water Distribution Networks =====
-The [[http://iridia.ulb.ac.be/~manuel/doc/cec2005-presentation.pdf|optimization of the operations of Water Distribution Networks]] may save important amounts of energy and its associated costs, and, therefore, it is an important problem in practice. There are [[http://www.epa.gov/nrmrl/wswrd/dw/epanet.html|graphical tools and simulators]] available. In addition, several optimization methods based on [[http://iridia.ulb.ac.be/~manuel/doc/cec2005.pdf|evolutionary algorithms]] and [[http://dx.doi.org/10.1061/(ASCE)0733-9496(2008)134:4(337)|ant colony optimization]] have been proposed in the literature. The goal of this project is to integrate the optimization algorithms into a graphical environment that can be used by water engineers and operators. No knowledge about water distribution networks is necessary. The optimisation algorithms and toolkit libraries for handling water distribution networks will be available to the student.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]
-===== Automatic fine-tuning of an evolutionary multi-objective framework =====
-The goal of this project is to explore the possibilities of using automatic configuration tools for fine-tuning an existing [[http://paradiseo.gforge.inria.fr/index.php?n=Paradiseo.MOEO|evolutionary multi-objective framework]]. The student will learn about automatic configuration tools, evolutionary algorithms for multi-objective optimization problems and analysis and comparison of multi-objective algorithms.
-  * Contacts :
-    * [[http://iridia.ulb.ac.be/~manuel|Manuel López-Ibáñez (IRIDIA)]]
-    * [[http://iridia.ulb.ac.be/~stuetzle|Thomas Stützle (IRIDIA)]]