Results 11 to 20 of about 259,517 (255)
Catecholaminergic modulation of meta-learning [PDF]
eLife, 2019 The remarkable expedience of human learning is thought to be underpinned by meta-learning, whereby slow accumulative learning processes are rapidly adjusted to the current learning environment. To date, the neurobiological implementation of meta-learning
Jennifer L Cook +6 more
doaj +3 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
Fernando, Chrisantha Thomas +8 more
core +2 more sources
2022 26th International Conference on Pattern Recognition (ICPR), 2022 Diese Dissertation untersucht die wissenschaftlichen Grundlagen selbstlernender Systeme und des maschinellen Wissenstransfers. In praktischen Herausforderungen zeigt sich der Nutzen von Transferlernmethoden zur Komplexitätsreduktion. Um ein systematisches Herangehen an das Transferlernen zu ermöglichen, wird die neue Methode des \(\textit {Transfer ...
Nico Zengeler +2 more
openaire +2 more sources
Meta Learning via Learned Loss [PDF]
2020 25th International Conference on Pattern Recognition (ICPR), 2021 Project website with code and video at https://sites.google.com/view ...
Bechtle, Sarah +6 more
openaire +3 more sources
Towards Explainable Meta-learning [PDF]
, 2021 Meta-learning is a field that aims at discovering how different machine learning algorithms perform on a wide range of predictive tasks. Such knowledge speeds up the hyperparameter tuning or feature engineering. With the use of surrogate models various aspects of the predictive task such as meta-features, landmarker models e.t.c.
Katarzyna Woźnica, Przemysław Biecek
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 +5 more
openaire +4 more sources
Learning Meta-Learning (LML) dataset: Survey data of meta-learning parameters
Data in Brief, 2023 L'ensemble de données « Learning Meta-Learning » présenté dans cet article contient à la fois des données catégorielles et continues d'apprenants adultes pour 7 paramètres de méta-apprentissage : âge, sexe, degré d'illusion de compétence, durée du sommeil, chronotype, expérience du phénomène de l'imposteur et intelligences multiples.
Sonia Corraya +2 more
openaire +3 more sources
, 2013 In: Encyclopedia of Systems Biology, W. Dubitzky, O. Wolkenhauer, K-H Cho, H. Yokota (Eds.), Springer 2011 Meta-learning methods are aimed at automatic discovery of interesting models of data. They belong to a branch of Machine Learning that tries to replace human experts involved in the Data Mining process of creating various computational models ...
+5 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. +3 more
openaire +4 more sources
Hierarchical meta-rules for scalable meta-learning [PDF]
, 2014 The Pairwise Meta-Rules (PMR) method proposed in [18] has been shown to improve the predictive performances of several metalearning algorithms for the algorithm ranking problem.
Pfahringer, Bernhard, Sun, Quan
core +2 more sources