Next Meetup

TensorFlow.js
Title: TensorFlow.js Summary: TensorFlow.js enables training and applying ML models in a web browser or in node.js. To get a sense of the possibilities and limitations of the framework, we'll first have a go at a text classification problem, demonstrating the training and application of a model. Then we'll take a shot at the problem of inferring a function name given its code. This problem has interesting applications to create intelligent developer tooling. As a cool side effect, we will introduce ways to analyze code efficiently, with readily available open source software. Bio: Vadim Markovtsev (https://github.com/vmarkovtsev) is a Google Developer Expert in Machine Learning and a Lead Machine Learning Engineer at source{d} (sourced.tech) where he works with "big natural code". His academic background is compiler technologies and system programming. Vadim is an open source zealot and an open data knight. References: 1. something about modern JavaScript: https://github.com/micromata/awesome-javascript-learning 2. something about TensorFlow: https://www.tensorflow.org/guide/low_level_intro and https://medium.com/the-artificial-impostor/notes-understanding-tensorflow-part-1-5f0ebb253ad4

Epitech

18 rue Flandres Dunkerque · Nantes

What we're about

Nous sommes développeurs et chercheurs avec un intérêt dans l'apprentissage automatique. Nous nous retrouverons pour discuter concrètement nos projets dans l'apprentissage automatique, réseau de neurones artificiels, modèles graphiques probabilistes, et traitement automatique du langage naturel.

-

We're developers and scientists interested in Machine Learning, Probabilistic Graphical Models, Neural networks, and Natural Language Processing. In this meetup, we'll bring together machine learning practitioners and researchers to listen to each other's work.

Members (1,535)

Photos (22)