**Êtes-vous un étudiant de l'EPFL à la recherche d'un projet de semestre?**

Travaillez avec nous sur des projets en science des données et en visualisation, et déployez votre projet sous forme d'application sur GraphSearch.

Concept# Multi-task learning

Résumé

Multi-task learning (MTL) is a subfield of machine learning in which multiple learning tasks are solved at the same time, while exploiting commonalities and differences across tasks. This can result in improved learning efficiency and prediction accuracy for the task-specific models, when compared to training the models separately. Early versions of MTL were called "hints".
In a widely cited 1997 paper, Rich Caruana gave the following characterization:Multitask Learning is an approach to inductive transfer that improves generalization by using the domain information contained in the training signals of related tasks as an inductive bias. It does this by learning tasks in parallel while using a shared representation; what is learned for each task can help other tasks be learned better.
In the classification context, MTL aims to improve the performance of multiple classification tasks by learning them jointly. One example is a spam-filter, which can be treated as distinct but related c

Source officielle

Cette page est générée automatiquement et peut contenir des informations qui ne sont pas correctes, complètes, à jour ou pertinentes par rapport à votre recherche. Il en va de même pour toutes les autres pages de ce site. Veillez à vérifier les informations auprès des sources officielles de l'EPFL.

Publications associées

Chargement

Personnes associées

Chargement

Unités associées

Chargement

Concepts associés

Chargement

Cours associés

Chargement

Séances de cours associées

Chargement

Concepts associés (2)

Réseau de neurones artificiels

Un réseau de neurones artificiels, ou réseau neuronal artificiel, est un système dont la conception est à l'origine schématiquement inspirée du fonctionnement des neurones biologique

Régularisation (mathématiques)

vignette|Les courbes bleues et vertes correspondent à deux modèles differents, tous les deux étant des solutions possibles du problème consistant à décrire les coordonnées de tous les points rouges. L

Cours associés (4)

BIO-322: Introduction to machine learning for bioengineers

Students understand basic concepts and methods of machine learning. They can describe them in mathematical terms and can apply them to data using a high-level programming language (julia/python/R).

CS-503: Visual intelligence : machines and minds

The course will discuss classic material as well as recent advances in computer vision and machine learning relevant to processing visual data with a primary focus on embodied intelligence and vision for active agents.

CS-233(a): Introduction to machine learning (BA3)

Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented.

Publications associées (68)

Chargement

Chargement

Chargement

Personnes associées (6)

Unités associées (3)

Séances de cours associées (6)

Many state-of-the-art approaches for Multi Kernel Learning (MKL) struggle at finding a compromise between performance, sparsity of the solution and speed of the optimization process. In this paper we look at the MKL problem at the same time from a learning and optimization point of view. So, instead of designing a regularizer and then struggling to find an efficient method to minimize it, we design the regularizer while keeping the optimization algorithm in mind. Hence, we introduce a novel MKL formulation, which mixes elements of p-norm and elastic-net kind of regularization. We also propose a fast stochastic gradient descent method that solves the novel MKL formulation. We show theoretically and empirically that our method has 1) state-of-the-art performance on many classification tasks; 2) ex- act sparse solutions with a tunable level of sparsity; 3) a convergence rate bound that depends only logarithmically on the num- ber of kernels used, and is independent of the sparsity required; 4) independence on the particular convex loss function used.

Oguzhan Fatih Kar, Amir Roshan Zamir, Shuqing Teresa Yeo

We present a method for making neural network predictions robust to shifts from the training data distribution. The proposed method is based on making predictions via a diverse set of cues (called 'middle domains') and ensembling them into one strong prediction. The premise of the idea is that predictions made via different cues respond differently to a distribution shift, hence one should be able to merge them into one robust final prediction. We perform the merging in a straightforward but principled manner based on the uncertainty associated with each prediction. The evaluations are performed using multiple tasks and datasets (Taskonomy, Replica, ImageNet, CIFAR) under a wide range of adversarial and non-adversarial distribution shifts which demonstrate the proposed method is considerably more robust than its standard learning counterpart, conventional deep ensembles, and several other baselines.

Many state-of-the-art approaches for Multi Kernel Learning (MKL) struggle at finding a compromise between performance, sparsity of the solution and speed of the optimization process. In this paper we look at the MKL problem at the same time from a learning and optimization point of view. So, instead of designing a regularizer and then struggling to find an efficient method to minimize it, we design the regularizer while keeping the optimization algorithm in mind. Hence, we introduce a novel MKL formulation, which mixes elements of p-norm and elastic-net kind of regularization. We also propose a fast stochastic gradient descent method that solves the novel MKL formulation. We show theoretically and empirically that our method has 1) state-of-the-art performance on many classification tasks; 2) ex- act sparse solutions with a tunable level of sparsity; 3) a convergence rate bound that depends only logarithmically on the num- ber of kernels used, and is independent of the sparsity required; 4) independence on the particular convex loss function used.

2011