A survey of transfer learning
Обзор трансферного обучения
2016-05-27
SCID: 54.1/fzcwsw9j
Discuss with AI
big datadata miningdomain adaptationmachine learningtransfer learning
Figures from the paper
Abstract (AI)
Machine learning and data mining techniques have been used in numerous real-world applications. An assumption of traditional machine learning methodologies is the training data and testing data are taken from the same domain, such that the input feature space and data distribution characteristics are the same. However, in some real-world machine learning scenarios, this assumption does not hold. There are cases where training data is expensive or difficult to collect. Therefore, there is a need to create high-performance learners trained with more easily obtained data from different domains. This methodology is referred to as transfer learning. This survey paper formally defines transfer learning, presents information on current solutions, and reviews applications applied to transfer learning. Lastly, there is information listed on software downloads for various transfer learning solutions and a discussion of possible future research work. The transfer learning solutions surveyed are independent of data size and can be applied to big data environments.
Key Findings
1
The survey formally defines transfer learning and reviews existing methods, applications, software implementations, and future research directions.
2
The surveyed transfer-learning solutions are described as independent of data size and applicable to big-data environments.
3
Traditional machine learning assumes training and testing data share the same feature space and distribution, an assumption often violated in real-world applications.
4
Transfer learning addresses limited or costly labeled data by training learners with more accessible data from different domains.
Research Object
Transfer learning (the methodology of training models on data from one domain to apply to a different target domain)
Research Subject
methods, applications, and performance of transferring knowledge from easily obtained source-domain data to learners operating in a different target domain
Publication Details
Publication Date
2016-05-27
Journal
Publisher
ISSN
Cited by
6245
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai1
Cited by16
A survey on Image Data Augmentation for Deep Learning2019
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions2021
Continual lifelong learning with neural networks: A review2019
Recent advances and applications of machine learning in solid-state materials science2019
Text Data Augmentation for Deep Learning2021
Human-in-the-loop machine learning: a state of the art2022
Social media data for conservation science: A methodological overview2019
A survey on data‐efficient algorithms in big data era2021
Augmenting organizational decision-making with deep learning algorithms: Principles, promises, and challenges2020
Constructing knowledge graphs and their biomedical applications2020
Google Earth Engine and Artificial Intelligence (AI): A Comprehensive Review2022
Non-Invasive Brain-Computer Interfaces: State of the Art and Trends2024
Artificial Intelligence and Advanced Materials2022
Integrating deep learning and discrete cosine transform for surface waves full-waveform inversion2024
Deploying Machine Learning for Radiography of Aerospace Welds2024
Detection of Cytopathic Effects Induced by Influenza, Parainfluenza, and Enterovirus Using Deep Convolution Neural Network2021