Accueil/ recherche

Recherche


Data Science Colloquium

16 résultat(s) sur le site


> Vous pouvez aussi chercher parmi nos archives

Affiner la recherche


Expression exacte Du
L'un des mots suivants Au
Tous les mots suivants
Ne contenant pas les mots suivants
Exposés (16)  Titre        Date 
photoExpose
Generative modelling with diffusion : theory and practice
Valentin De Bortoli
25/05/2023
« Generative modelling with diffusion : theory and practice » Generative modelling with diffusion: theory and practice Generative modeling is the task of drawing new samples from an underlying distribution known only via an empirical measure. Th...
Catégories : Data Science Colloquium
Mots-clefs: modélisation, machine learning, intelligence artificielle
photoExpose
Prototype-based classifiers and relevance learning
Michael Biehl
27/02/2020
Exposé de Michael Biehl (University of Groningen) dans le cadre du Data Science Colloqiuum de l'ENS.  This talk briefly reviews important aspects of prototype based systems in the context of supervised learning. A key issue is the choice of an appr...
Catégories : Data Science Colloquium
Mots-clefs: Médecine, image 3D, machine learning, intelligence artificielle
photoExpose
Reverse Engineering Visual Intelligence
Jim DiCarlo
14/01/2020
Conférence de Jim DiCarlo (MIT) dans le cadre du Colloquium du département d'Etudes Cognitives de l'ENS. The brain and cognitive sciences are hard at work on a great scientific quest — to reverse engineer the human mind and its intelligent behavior...
Catégories : Colloquium du DEC
Mots-clefs: perception visuelle, cerveau, Nouvelles technologies, réseau neuronal, vision, intelligence artificielle
photoExpose
Optimization's Hidden Gift to Learning: Implicit Regularization
Nathan Srebro
01/10/2019
Exposé de Nathan Srebro dans le cadre du Data Science Colloqiuum de l'ENS.  It is becoming increasingly clear that implicit regularization afforded by the optimization algorithms play a central role in machine learning, and especially so whe...
Catégories : Data Science Colloquium
Mots-clefs: mathématiques, algorithme, machine learning
photoExpose
Towards developmental AI
Emmanuel Dupoux
17/10/2018
Conférence d'Emmanuel Dupoux lors du Data Science Colloquium de l'ENS. Even though current machine learning techniques yield systems that achieve parity with humans on several high level tasks, the learning algorithms themselves are orders of magni...
Catégories : Data Science Colloquium
Mots-clefs: Langage, enfant, apprentissage, sciences cognitives, algorithme, machine learning, intelligence artificielle, ...
photoExpose
Learning Graph Inverse Problems with Neural Networks
Joan Bruna
12/06/2018
Conférence de Joan Bruna lors du Data Science Colloquium de l'ENS. Graph Neural Networks, a natural extension of Convolutional Neural Networks on graphs. I will present recent work on supervised community detection, quadratic assignment, neutrino d...
Catégories : Data Science Colloquium
Mots-clefs: mathématiques, algorithme, signal, ordinateur, machine learning, apprentissage automatique
photoExpose
Machine learning in scientific workflows
Balàzs Kégl
15/05/2018
Conférence de Balázs Kégl (Université Paris Saclay) dans le cadre du Data Science Colloqium, série de conférences de la Chaire CFM-­ENS "Modèles et Sciences des Données". I will describe our contributions to scientific ML workflow building and op...
Catégories : Data Science Colloquium
Mots-clefs: base de données, prévision, machine learning, intelligence artificielle, Open data, apprentissage automatique
photoExpose
Brain-computer interfaces: two concurrent learning problems
Maureen Clerc
06/02/2018
Conférence de Maureen Clerc lors du Data Science Colloquium de l'ENS. Brain-Computer Interfaces (BCI) are systems which provide real-time interaction through brain activity, bypassing traditional interfaces such as keyboard or mouse. A target appli...
Catégories : Data Science Colloquium
Mots-clefs: mathématiques, Neurosciences, cerveau, modélisation, interaction, signal, interface, ordinateur, machine learning, ...
photoExpose
Searching for interaction networks in proteins
Rémi Monasson
14/11/2017
Conférence de Rémi Monasson lors du colloquium Data Science Colloquium of the ENS   Searching for interaction networks in proteins: from statistical physics to machine learning, and back. Over the last century, statistical physics was extremely su...
Catégories : Data Science Colloquium
Mots-clefs: Biologie, physique, protéine, interaction, Big Data, machine learning, intelligence artificielle
photoExpose
Cosmostatistics: Tackling Big Data from the Sky
Jean-Luc Starck
03/10/2017
Conférence de Jean-Luc Starck lors du colloquium Data Science Colloquium de l'ENS. Since the dawn of time, humans have been wondering about their place in the Universe. Over the past century, advances in modern physics, technology and engineering, ...
Catégories : Data Science Colloquium
Mots-clefs: Astrophysique, cosmologie, statistique, Big Data
photoExpose
The brain as an optimal efficient adaptive learner
Sophie Deneve
16/05/2017
Conférence de Sophie Deneve lors du colloquium Data Science Colloquium  de l'ENS. Understanding how the brain learns to compute functions reliably, efficiently, and robustly with noisy spiking activity is a fundamental challenge in neuroscience. M...
Catégories : Data Science Colloquium
Mots-clefs: cerveau, apprentissage, Code, informatique, neurones, Big Data, machine learning, intelligence artificielle, erreur
photoExpose
Beyond stochastic gradient descent for large-scale machine learning
Francis Bach
07/03/2017
Conférence de Francis Bach lors du colloquium Data Science Colloquium of the ENS This colloquium is organized around data sciences in a broad sense, with the goal of bringing together researchers with diverse backgrounds (including mathematics, ...
Catégories : Data Science Colloquium
Mots-clefs: Stochastique, Big Data, machine learning, intelligence artificielle
photoExpose
What physics can tell us about inference ?
Cristopher Moore
08/11/2016
Conférence de Cristopher Moore lors du colloquium Data Science Colloquium of the ENS This colloquium is organized around data sciences in a broad sense, with the goal of bringing together researchers with diverse backgrounds (including mathematics, ...
Catégories : Data Science Colloquium
Mots-clefs: base de données, informatique, algorithme, interdisciplinarité, interprétation, physique statistique, ordinateur, ...
photoExpose
Can Big Data cure Cancer?
Jean-Philippe Vert
11/10/2016
Conférence de Jean-Philippe Vert lors du colloquium Data Science Colloquium of the ENS This colloquium is organized around data sciences in a broad sense, with the goal of bringing together researchers with diverse backgrounds (including mathematic...
Catégories : Data Science Colloquium
Mots-clefs: Biologie, ADN, Médecine, cancer, Nouvelles technologies, informatique, pathologie, Big Data, interdisciplinarité, ...
photoExpose
The new role of time and events in computer science
Gérard Berry
09/04/2015
Conférence de Gérard Berry organisée par le département de Physique. During the 20th century, traditional computer science considered time only from the performance angle, i.e., as a major complexity measures for algorithms, circuits and programs. B...
Catégories : Colloquium / Séminaire général du département de physique
Mots-clefs: temps, temporalité, mesure, informatique
photoExpose
Statistical physics of compressed sensing
Marc Mézard
14/11/2013
Conférence de Marc Mézard Compressed sensing is a major new topic in information theory. Starting from the observation that interesting signals can be compressed, and thus are sparse in some representation, it aims at acquiring data directly in a co...
Catégories : Colloquium / Séminaire général du département de physique
Mots-clefs: mathématiques, Code, information, algorithme, physique statistique, acquisition compressée