Results 1 to 10 of about 245,952 (212)

A survey of deep meta-learning [PDF]

Artificial Intelligence Review, 2021
AbstractDeep neural networks can achieve great successes when presented with large data sets and sufficient computational resources. However, their ability to learn new conceptsquicklyis limited. Meta-learning is one approach to address this issue, by enabling the network to learn how to learn. The field ofDeep Meta-Learningadvances at great speed, but
Mike Huisman, Jan N. van Rijn, Aske Plaat   +2 more
openaire   +4 more sources

Meta-learning by the Baldwin effect [PDF]

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2018
The scope of the Baldwin effect was recently called into question by two papers that closely examined the seminal work of Hinton and Nowlan. To this date there has been no demonstration of its necessity in empirically challenging tasks. Here we show that the Baldwin effect is capable of evolving few-shot supervised and reinforcement learning mechanisms,
Chrisantha Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang 0001, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu   +8 more
openaire   +2 more sources

Bootstrapped Meta-Learning

CoRR, 2021
Published at ICLR 2022.
Sebastian Flennerhag, Yannick Schroecker, Tom Zahavy, Hado van Hasselt, David Silver 0001, Satinder Singh 0001   +5 more
openaire   +3 more sources

Meta-Learning to Compositionally Generalize [PDF]

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 2021
ACL2021 Camera Ready; fix a small ...
Conklin, H., Wang, B., Smith, K., Titov, I.   +3 more
openaire   +4 more sources

Meta-Learning in Games

CoRR, 2022
In the literature on game-theoretic equilibrium finding, focus has mainly been on solving a single game in isolation. In practice, however, strategic interactions -- ranging from routing problems to online advertising auctions -- evolve dynamically, thereby leading to many similar games to be solved.
Keegan Harris, Ioannis Anagnostides, Gabriele Farina, Mikhail Khodak, Zhiwei Steven Wu, Tuomas Sandholm   +5 more
openaire   +2 more sources

Adversarial Meta-Learning

CoRR, 2018
11 ...
Chengxiang Yin 0001, Jian Tang 0008, Zhiyuan Xu, Yanzhi Wang 0001   +3 more
openaire   +2 more sources

Weighted Meta-Learning

CoRR, 2020
Meta-learning leverages related source tasks to learn an initialization that can be quickly fine-tuned to a target task with limited labeled examples. However, many popular meta-learning algorithms, such as model-agnostic meta-learning (MAML), only assume access to the target samples for fine-tuning.
Diana Cai, Rishit Sheth, Lester Mackey, Nicoló Fusi   +3 more
openaire   +2 more sources

Meta-learned models of cognition

Behavioral and Brain Sciences, 2023
Abstract Psychologists and neuroscientists extensively rely on computational models for studying and analyzing the human mind. Traditionally, such computational models have been hand-designed by expert researchers. Two prominent examples are cognitive architectures and Bayesian models of cognition. Although the former requires the specification of a
Marcel Binz, Ishita Dasgupta, Akshay K. Jagadish, Matthew Botvinick, Jane X. Wang, Eric Schulz   +5 more
openaire   +4 more sources

Modular meta-learning

CoRR, 2018
Presented at CoRL ...
Ferran Alet, Tomás Lozano-Pérez, Leslie Pack Kaelbling   +2 more
openaire   +3 more sources

Hierarchical Meta Learning

CoRR, 2019
Meta learning is a promising solution to few-shot learning problems. However, existing meta learning methods are restricted to the scenarios where training and application tasks share the same out-put structure. To obtain a meta model applicable to the tasks with new structures, it is required to collect new training data and repeat the time-consuming ...
Yingtian Zou, Jiashi Feng
openaire   +2 more sources