Julien Hubar's Projects
In a game of chess, each move is made according to astrategy that aims to optimize the situation of the activeplayer. The evaluation of the position of the differentpieces is therefore a central issue that we will be tack-ling in this project. The goal we fixed ourselves is touse an evaluation of the board positions through a con-volutional neural network (CNN). This evaluation aimsto mimic the complex heuristic of the well known chessengineStockfish. We will then use this learned evaluationas the heuristic in aminimaxalgorithm to implement ourown chess AI.
GitHub profile
This is a flutter plugin to detect edges in a live camera, take the picture of detected edges object, crop it, and save.
These projects were carried out as part of the MATH2021-1 High-dimensional data analysis course of the ULiege.
Lectures for INFO8010 - Deep Learning, ULiège
This my resume code source
In order to safely shepherd a rocket to a circular orbit of about 100 km, it is imperative to ensure a good consistency and availability of the computing resources used to guide the rocket. One way to achieve this is to rely on a cluster of computers collaborating to guide the rocket, using distributed algorithms. Our implementation will leverage a modification of the Raft consensus algorithm
projet1
Compressive sensing exploit the possibility to represent an image with a sparse representation.
Modeling epidemic using bayesian Bayesian inference and SEIR+ model
Privacy-in-household-robots
Information theory provides a quantitative measure of the information provided by a message or an observation. This notion was introduced by Claude Shannon in 1948 in order to establish the limits of what is possible in terms of data compression and transmission over noisy channels. Since these times, this theory has found many applications in telecommunications, computer science ans statistics. The course is composed of three parts