Monday, May 12, 2014

Paris Machine Learning Meetup #11: Learning, What Is It Good For ?

This coming Wednesday evening, we will be having the 11th Paris Machine Learning Meetup. This is one meetup before last for Season 1. Criteo will be hosting us and we currently expect about three presentations, two of which will be remote. Franck and I will talk about the big surprise for the last meetup (meetup#12) and our plans for Season 2. If you want to be part of the 840+ members of the group, register here. Here are the speakers with a short abstract of their presentations:

+ Andrew Lan (SPARFA, Rice University,

Title -- SPARFA: Sparse Factor Analysis for Learning and Content Analytics. 

Abstract: We develop SPARFA and its various extensions, a set of models and algorithms for machine-learning-based personalized education. 

+ Leon Bottou (Microsoft Research, ML group,

Title -- Learning to Interact 

Abstract -- Understanding the subtle connection between correlation and causation is critical for engineers building online systems that interact with users. 

Title -- Object and action recognition with Convolutional Neural Networks. 

Abstract -- We show how image representations learned with CNNs on large-scale annotated datasets can be efficiently transferred to other visual recognition tasks with limited amount of training data. 

We will also have alightning talk:

Louis Dorard , Les API de prédiction

Abstract: Les API de prédiction abstraient une grande partie de la complexité liée à la construction de modèles prédictifs et à leur déploiement. Elles présentent de nombreux avantages pour ceux qui débutent dans le Machine Learning, mais aussi pour les "aficionados". 

We will probably have a Google Hangout for those who cannot make it, more details to follow.

No comments: