Transfer learning
Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. For example, knowledge gained while learning to recognize cars could apply when trying to recognize trucks. This area of research bears some relation to the long history of psychological literature on transfer of learning, although formal ties between the two fields are limited. From the practical standpoint, reusing or transferring information from previously learned tasks for the learning of new tasks has the potential to significantly improve the sample efficiency of a reinforcement learning agent.
Wikipage redirect
Admissible heuristicArtificial general intelligenceArtificial intelligenceAutomated machine learningCatastrophic interferenceComputational humorConvolutional neural networkData augmentationDeep learningDiffusion waveletsDomain adaptationDysmorphic featureGeneral game playingGenerative adversarial networkGlobal Information Network ArchitectureHuman image synthesisInductive transferKernel methods for vector outputMackenzie Weygandt MathisManifold alignmentMeta learning (computer science)Multi-task learningMultitask optimizationMurray ShanahanOutline of machine learningOutline of object recognitionReinforcement learningRonald SummersSpeech synthesisSynthetic dataTransformer (machine learning model)Weak supervision
Link from a Wikipage to another Wikipage
differentFrom
primaryTopic
Transfer learning
Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. For example, knowledge gained while learning to recognize cars could apply when trying to recognize trucks. This area of research bears some relation to the long history of psychological literature on transfer of learning, although formal ties between the two fields are limited. From the practical standpoint, reusing or transferring information from previously learned tasks for the learning of new tasks has the potential to significantly improve the sample efficiency of a reinforcement learning agent.
has abstract
L'apprentissage par transfert ...... es partageant des similitudes.
@fr
Transfer learning (TL) is a re ...... reinforcement learning agent.
@en
Передава́льне навча́ння (ПН, а ...... ента навчання з підкріпленням.
@uk
迁移学习 是属于机器学习的一种研究领域。它专注于存储已有问题 ...... 迁移在概念上有一定关系,但是两个领域在学术上的关系非常有限。
@zh
Wikipage page ID
page length (characters) of wiki page
Wikipage revision ID
1,022,394,104
Link from a Wikipage to another Wikipage
wikiPageUsesTemplate
subject
comment
L'apprentissage par transfert ...... es partageant des similitudes.
@fr
Transfer learning (TL) is a re ...... reinforcement learning agent.
@en
Передава́льне навча́ння (ПН, а ...... ента навчання з підкріпленням.
@uk
迁移学习 是属于机器学习的一种研究领域。它专注于存储已有问题 ...... 迁移在概念上有一定关系,但是两个领域在学术上的关系非常有限。
@zh
label
Apprentissage par transfert
@fr
Transfer learning
@en
Передавальне навчання
@uk
迁移学习
@zh