Glossary/Glossaire

Apprentissage  statistique / Machine learning

Machine learning is a field of computer science that gives computers the ability to “learn” to perform a task from data, without being explicitly programmed. Machine Learning can be “supervised”, or “unsupervised”. In Supervised Machine Learning, the learning algorithms are provided with data made of inputs and expected outputs, and the task is to predict the correct output for new inputs. In Unsupervised Machine Learning, the task mostly consists in finding hidden patterns in unlabelled data. One possible method for (supervised) Machine Learning is Deep Learning.

Applications: Computer Vision (Vincent Lepetit, ADD MORE PEOPLE), ADD MORE APPLICATIONS

Apprentissage profond / Deep Learning

Deep learning is one possible method for Machine learning. It is based on Deep Networks, which are loosely inspired by biological neural networks, but can be efficiently implemented on computers, especially when GPUs are used. Deep Learning performs extremely well for supervised machine learning problems when a large amount of training data is available.

Applications: Computer Vision (Vincent Lepetit, ADD MORE PEOPLE), ADD MORE APPLICATIONS

Apprentissage par renforcement/ Reinforcement learning
Big Data
Agent conversationnel / Chatbot
Cobotique
Internet des objets / Internet of Things (IoT)
Reconnaissance de formes
Réseau neuronal / Neural Network and Deep Network
Robot
Système expert / Expert System
Test de Turing / Turing Test