Feb 7Member-onlyIntroduction à la simulation avec NetLogo : comment créer une petite usine ?NetLogo a été conçu comme un logiciel d’introduction à un type de simulation qui permet de mettre en action plusieurs agents, chacun avec son comportement propre. Aussi connue sous le nom d’Agent Based Modeling. Dans les faits, ce logiciel est utilisé professionnellement, en particulier pour les simulations sociales, en épidémiologie…Usine13 min read
Feb 7Member-onlyIntroduction to simulation with NetLogo: how to create a small factory?NetLogo was designed as an introduction to a type of simulation that allows putting into action several agents, each with its own behavior. Also known as Agent-Based Modeling. This software is also used professionally, especially for social simulations, in epidemiology and biology. It is accessible without any prior knowledge of…Netlogo13 min read
Feb 7Que peut apporter l’IA au contrôle qualité dans l’Industrie ?L’arrivée des réseaux de neurones convolutifs a été une révolution dans le domaine de la vision par ordinateur, qui a démultiplié les performances des algorithmes. En partant d’un réseau de neurones sur étagère, pré-entraînée sur des centaines de milliers d’images, il est désormais possible d’apprendre en quelques coups à trier…Industrie10 min read
Jan 25Member-onlyAn overview of Picsellia, an MLOps platform for computer vision.I was able to attend a demo of this product recently, and it warrants your interest. I am not affiliated with Picsellia, the goal is to allow people to discover this product and the MLOps practices it allows. Picsellia offers a one-of-a-kind product. After HuggingFace, we could be in front…Mlops5 min read
Jan 25Member-onlyUn aperçu de Picsellia, la plateforme de MLOps française pour la vision par ordinateur.J’ai pu assister récemment à une démo de ce produit, et c’est assez intéressant pour que je vous en parle. Je ne suis pas affilié à Picsellia, le but est de permettre de découvrir ce produit et les pratiques de MLOps qu’il permet. Picsellia est une entreprise basée à Toulouse…Mlops5 min read
Jan 20Member-onlyThe current landscape of MLOpsFind your way in the jungle of MLOps solutions It is not a new story. When Machine Learning projects reach a critical size, things become difficult to handle with traditional tools. Here are some challenges for MLOps and some solutions that can be deployed… Handling the Data Creation In many real-world applications, the data…Machine Learning26 min read
Sep 22, 2021Member-onlyA cheat sheet for statistical estimatorsWhat distribution and parameters fit our data? What is the confidence interval of the estimated parameters? — The above article contains the formulas with minimal explanations. If you have seen this topic some time ago, it is probably a good way to refresh memories. However, this would be a bit too harsh to start from scratch with it. …Statistics10 min read
Aug 27, 2021Member-onlyAn introduction to classification algorithmsIn the precedent article, I spoke about the creation of a Bag of Words in R. Then, I made tests on two different datasets. This is a good occasion to tell a little about some commonly used classification algorithms. I will give some code samples in R, but this is…Classification15 min read
Aug 25, 2021Member-onlyHow to create a Bag of Words embedding in R?Bag of Word embedding is a Natural Language Processing technic to embed sentences into a fixed-size numeric vector. The goal is to use this vector as an input for a machine learning algorithm. Bag of Words is simple to understand an is a great technic when you want to keep…R9 min read
May 11, 2021Member-onlyA glimpse of the maths behind Optimization AlgorithmsOk, let’s start… (∩｀-´)⊃━☆ﾟ.*･｡ﾟ import numpy as np from scipy.optimize import minimize End… No? Ok… ¯\_(ツ)_/¯ We need to dive a bit more into maths… The goal of this article is to provide a basic understanding of the maths behind common types of optimization algorithms. I used both my notes…Neural Networks14 min read
