Algorithme d'apprentissage incrémental

Résumé

En informatique, un algorithme d'apprentissage incrémental ou incrémentiel est un algorithme d'apprentissage qui a la particularité d'être online, c'est-à-dire qui apprend à partir de données reçues au fur et à mesure du temps. À chaque incrément il reçoit des données d'entrées et un résultat, l'algorithme calcule alors une amélioration du calcul fait pour prédire le résultat à partir des données d'entrées. Principe Analyse compétitive Puisqu'il ne connait pas l'intégralité des données, un algorithme d'apprentissage incrémental est forcé de faire des choix qui peuvent s'avérer finalement non optimaux ; l'étude des algorithmes d'apprentissage incrémental a ainsi mis l'accent sur la qualité des choix possibles dans une telle configuration. L'analyse compétitive formalise cette idée en comparant la performance, sur les mêmes données, de l'algorithme d'apprentissage incrémental et de l'équivalent ayant à disposition l'intégralité des données. Pour d'autres points de

Source officielle

https://fr.wikipedia.org/wiki/Algorithme_d'apprentissage_incr%C3%A9mental

À propos de ce résultat

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 (42)

Publications associées

Chargement

Personnes associées (4)

Personnes associées

Chargement

Unités associées (2)

Unités associées

Chargement

Concepts associés (6)

Le perceptron est un algorithme d'apprentissage supervisé de classifieurs binaires (c'est-à-dire séparant deux classes). Il a été inventé en 1957 par Frank Rosenblatt au laboratoire d'aéronautique de

L'algorithme du gradient stochastique est une méthode de descente de gradient (itérative) utilisée pour la minimisation d'une fonction objectif qui est écrite comme une somme de fonctions différentiab

L'apprentissage automatique (en anglais : machine learning, « apprentissage machine »), apprentissage artificiel ou apprentissage statistique est

Afficher plus

Concepts associés

Chargement

Cours associés (10)

Cours associés

Chargement

Séances de cours associées (10)

Séances de cours associées

Chargement

Artificial intelligence (AI) and machine learning (ML) have become de facto tools in many real-life applications to offer a wide range of benefits for individuals and our society. A classic ML model is typically trained with a large-scale static dataset in an offline manner. Therefore, it can not quickly capture new knowledge in non-stationary environments, and it is difficult to maintain long-term memory for knowledge learned earlier. In practice, many ML systems often need to learn new knowledge (e.g., domains, tasks, distributions, etc.) as more data and experiences are collected, which is referred to as a lifelong ML paradigm in this thesis. We focus on two fundamental challenges to achieve lifelong learning. The first challenge is to quickly learn new knowledge with a small number of observations, and we refer to it as data efficiency. The second challenge is to prevent an ML system from forgetting the old knowledge it has previously learned, and we refer to this challenge as knowledge retention. These two capabilities are crucial for applying ML to most practical applications. In this thesis, we study three important applications with these two challenges, including recommendation systems, task-oriented dialog systems, and the image classification task. First, we propose two approaches to improve data efficiency for task-oriented dialog systems. The first proposed approach is based on Meta-learning, aiming to learn a better model parameter initialization from training data. It can quickly reach a good parameter region of new domains or tasks with a small number of labeled data. The second proposal takes a semi-supervised self-training approach to iteratively train a better model using sufficient unlabeled data when only a limited number of labeled data are available. We empirically demonstrate that both approaches effectively improve data efficiency to learn new knowledge. The second self-training method even consistently improves state-of-the-art large-scale pre-trained models. Second, we tackle the knowledge retention challenge to mitigate the detrimental catastrophic forgetting issue when neural networks learn new knowledge sequentially. We formulate and investigate the ``continual learning'' setting for task-oriented dialog systems and recommendation systems. Through extensive empirical evaluation and analysis, we demonstrate the importance of (1) exemplar replay: storing representative historical data and replaying them to the model while learning new knowledge; (2) dynamic regularization: applying a dynamic regularization term to put flexible constraints on not forgetting previously learned knowledge in each model update cycle. Lastly, we conduct several initial attempts to achieve both data efficiency and knowledge retention in a unified framework. In the recommendation scenario, we propose two approaches using different non-parametric memory modules to retain long-term knowledge. More importantly, the two proposed non-parametric predictions computed on top of them help learn and memorize new knowledge in a data-efficient manner. Apart from the recommendation scenario, we propose a probabilistic evaluation protocol in the widely studied image classification domain. It is general and versatile to simulate a wide range of realistic lifelong learning scenarios that require both knowledge retention and data efficiency for studying different techniques. Through experiments, we also demonstrate the benefit

EPFL2021

Chargement

An online Hebbian learning rule that performs Independent Component Analysis

Claudia Clopath, Wulfram Gerstner, André Longtin

Independent component analysis (ICA) is a powerful method to decouple signals. Most of the algorithms performing ICA do not consider the temporal correlations of the signal, but only higher moments of its amplitude distribution. Moreover, they require some preprocessing of the data (whitening) so as to remove second order correlations. In this paper, we are interested in understanding the neural mechanism responsible for solving ICA. We present an online learning rule that exploits delayed correlations in the input. This rule performs ICA by detecting joint variations in the firing rates of pre- and postsynaptic neurons, similar to a local rate-based Hebbian learning rule.

MIT Press2008

Chargement

Understanding the performance gap: a machine learning approach on residential buildings in Turin, Italy

Roberto Boghetti, Jérôme Henri Kämpf

Buildings account for the highest share of primary energy usage and greenhouse gas emission in the E.U. and U.S. [1], and most of this energy is used for space and water heating. Being able to gain a broader understanding of the gap between predicted and in situ measured thermal performance of buildings may, in a lot of cases, help reducing the energy consumption and, therefore, alleviating our pressure on the environment [2]. The aim of this research is to further investigate this performance gap and to evaluate the possibility of using machine learning algorithms to effectively predict the energy demand of buildings. For this purpose, a group of residential buildings in the city of Turin, Italy, is taken as case study: an estimation of their yearly heating demand is made using different machine learning algorithms, and their results are evaluated and discussed. The research showed that the use of machine learning resulted in a performance gap in line, if not lower, with the current literature. The reasons for this outcome, as well as possible future research directions are finally discussed.

IOP Publishing Ltd2019

Chargement

EPFL2021