Results 11 to 20 of about 1,532,491 (274)
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
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
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
IEEE Access, 2021 While the general belief is that the best way to predict electric load is through individualized models, the existing studies have focused on one-for-all models because the individual models are difficult to train and require a significantly larger data ...
Eunjung Lee, Wonjong Rhee
doaj +1 more source
Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond
IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023 Machine learning on electromyography (EMG) has recently achieved remarkable success on various tasks, while such success relies heavily on the assumption that the training and future data must be of the same data distribution.
Di Wu, Jie Yang, Mohamad Sawan
doaj +1 more source
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
Sharing learning experiences through correspondence on the WWW [PDF]
, 2001 Asynchronous learning networks are facilities and procedures to allow members of learning communities to be more effective and efficient in their learning.
Kommers, Piet
core +2 more sources
Meta Learn on Constrained Transfer Learning for Low Resource Cross Subject EEG Classification
IEEE Access, 2020 Electroencephalogram (EEG) signal has large variance and its pattern differs significantly across subjects. Cross subject EEG classification is a challenging task due to such pattern variation and the limited target data available, as collecting and ...
Tiehang Duan +6 more
doaj +1 more source
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
IEEE Access, 2023 China corporation bond default prediction is important and can be formulated as an imbalance classification problem solved by static ensemble classifiers. However, dynamic ensemble selection (DES) classifiers have not been applied to this typical problem
Yu Wang, Junbin Zhang, Wei Yan
doaj +1 more source