Conférences - Réseaux de neurones et intelligence artificielle, apprentissage automatique - n’importe où (en ligne)

Sélecionner un pays
1
Workshop on Advances in Theory and Algorithms for Deep Reinforcement Learning
02 aou 2021 - 04 aou 2021 • Virtually, n’importe où (en ligne)
Résumé:
There has been significant progress over the last few years in the theory and applications of Reinforcement Learning (RL). While RL theory and applications have had a rich history going back several decades, the major recent successes have occurred due to a successful marriage between deep learning approaches for function approximation embedded within a reinforcement learning framework for decision-making (Deep RL). On one hand, there has been a richer understanding of Stochastic Gradient Descent (SGD) for non-convex optimization, its impact in driving training error to zero in deep neural networks, and on the generalization ability of such networks for inference. On the other hand, there has been an explosion of research on iterative learning algorithms with strong statistical guarantees in the settings of reinforcement learning, stochastic approximation and multi-armed bandits.
Identifiant de l'évènement:
1423029
2
IJCAI 2021 DSO Workshop — Data Science meets Optimisation (DSO) Workshop at IJCAI-21
21 aou 2021 • virtual, n’importe où (en ligne)
Résumé:
Data science and optimization are closely related. On the one hand, many problems in data science can be solved using optimizers, on the other hand optimization problems stated through classical models such as those from mathematical programming cannot be considered independent of historical data. Examples are ample: Machine Learning (ML) often relies on optimization techniques such as linear or integer programming; reasoning systems have been applied to constrained pattern and sequence mining tasks; a parallel development of metaheuristic approaches has taken place in the domains of data mining and machine learning; methods aimed at high level combinatorial optimization have been shown to strongly profit from configuration, algorithm selection and tuning tools building on historical data; ML models can be embedded in combinatorial optimization problems to address hard-to-model systems, or for validation of the ML model itself; “predict, then optimize” scenarios can be dealt with in an integrated fashion to improve considerably the solution quality.
Identifiant de l'évènement:
1429081
Sujets apparentés:


Conference-Service.com met à la disposition de ses visiteurs des listes de conférences et réunions dans le domaine scientifique. Ces listes sont publiées pour le bénéfice des personnes qui cherchent une conférence, mais aussi, bien sûr, pour celui des organisateurs. Noter que, malgré tout le soin que nous apportons à la vérification des données entrées dans nos listes, nous ne pouvons accepter de responsabilité en ce qui concerne leur exactitude ou étendue. Pensez donc à vérifier les informations présentées avec les organisateurs de la conférence ou de la réunion avant de vous engager à y participer!

Dernière mise à jour: 04 Juin 2021