Huang, Junzhou, Wei, Ying, Yang, Qiang et al. · Rare & Special e-Zone (The Hong Kong University of Science and Technology) · 2018
In transfer learning, what and how to transfer are two primary issues to be addressed, as different transfer learning algorithms applied between a source and a target domain result in different knowledge transferred and thereby the performance improvement in the target domain. Determining the optimal one that maximizes the performance improvement requires either exhaustive exploration or considerable expertise. Meanwhile, it is widely accepted in educational psychology that human beings improve transfer learning skills of deciding what to transfer through meta-cognitive reflection on inductive transfer learning practices. Motivated by this, we propose a novel transfer learning framework known as Learning to Transfer (L2T) to automatically determine what and how to transfer are the best by leveraging previous transfer learning experiences. We establish the L2T framework in two stages: 1) we learn a reflection function encrypting transfer learning skills from experiences; and 2) we infer what and how to transfer are the best for a future pair of domains by optimizing the reflection function. We also theoretically analyse the algorithmic stability and generalization bound of L2T, and empirically demonstrate its superiority over several state-of-the-art transfer learning algorithms.
Cited by 0
Lisa Torrey, Jude Shavlik · IGI Global eBooks · 2010
Transfer learning is the improvement of learning in a new task through the transfer of knowledge from a related task that has already been learned. While most machine learning algorithms are designed to address single tasks, the development of algorithms that facilitate transfer learning is a topic of ongoing interest in the machine-learning community. This chapter provides an introduction to the goals, settings, and challenges of transfer learning. It surveys current research in this area, giving an overview of the state of the art and outlining the open problems. The survey covers transfer in both inductive learning and reinforcement learning, and discusses the issues of negative transfer and task mapping.
Cited by 1,423
Yinhai Wang, Zhiyong Cui, Ruimin Ke · Elsevier eBooks · 2023
Cited by 0
Henrik Biermann · 2024
Cited by 0
Louis Combe (14636891), Mélina Durande (14636894), Hélène Delanoë-Ayari (279118) et al. · Figshare · 2023
<p>A: Comparison of true and predicted long and short axes for the best 2-conv model (blue) and transfer from VGG19 (red). The black dashed line represents identity. B-C-D: distribution of absolute errors on the test set for all four models and for long axes (B), short axes (C) and orientation (D). E: Loss on validation set during the final training of each model as a function of the number of epochs. F: Loss on validation set as a function of time spent training.</p>
Cited by 0Open access
Osipenko, Sergey · Figshare · 2020
Here we present the source code and pre-trained models to predict retention times.<br>
Cited by 0Open access
Osipenko, Sergey · Figshare · 2020
Here we present the source code and pre-trained models to predict retention times.<br>
Cited by 0Open access
Meihua Zhou (12331454), Ivan Fung (13814059), Li Yang (6520) et al. · Figshare · 2024
<div><p>The rapid population growth in urban areas has led to an increased frequency of lost and unclaimed items in public spaces such as public transportation, restaurants, and other venues. Services like Find My iPhone efficiently track lost electronic devices, but many valuable items remain unmonitored, resulting in delays in reclaiming lost and found items. This research presents a method to streamline the search process by comparing images of lost and recovered items provided by owners with photos taken when items are registered as lost and found. A photo matching network is proposed, integrating the transfer learning capabilities of MobileNetV2 with the Convolutional Block Attention Module (CBAM) and utilizing perceptual hashing algorithms for their simplicity and speed. An Internet framework based on the Spring Boot system supports the development of an online lost and found image identification system. The implementation achieves a testing accuracy of 96.8%, utilizing only 0.67 GFLOPs and 3.5M training parameters, thus enabling the recognition of images in real-world scenarios and operable on standard laptops.</p></div>
Cited by 0Open access
Prof. Dr. Norbert M. Seel · 2012
Cited by 0
Edward Chmiel, Arlene Campos, Dimitrios Toumpanakis · Radiopaedia.org · 2019
Cited by 0Open access
WORLD SCIENTIFIC eBooks · 2025
Cited by 0
Qiang Yang, Yu Tong Shirley Zhang, Wenyuan Dai et al. · DR-NTU (Nanyang Technological University) · 2020
This book is about the foundations, methods, techniques and applications of transfer learning. Transfer learning deals with how learning systems can quickly adapt themselves to new situations, new tasks and new environments. Transfer learning is a particularly important area of machine learning, which we can understand from several angles. First, the ability to learn from small data seems to be a particularly strong aspect of human intelligence. For example, we observe that babies learn from only a few examples and can quickly and effectively generalize from the few examples to concepts. This ability to learn from small data can be partly explained by the ability of humans to leverage and adapt the previous experience and pre-trained models to help solve future target problems. Adaptation is an innate ability of intelligent beings and artificially intelligent agents should certainly be endowed with transfer-learning ability-- | Instance-based transfer learning -- | Feature-based transfer learning -- | Model-based transfer learning -- | Relation-based transfer learning -- | Heterogeneous transfer learning -- | Adversarial transfer learning -- | Transfer learning in reinforcement learning -- | Multi-task learning -- | Transfer learning theory -- | Transitive transfer learning -- | AutoTL : learning to transfer automatically -- | Few-shot learning -- | Lifelong machine learning -- | Privacy-preserving transfer learning -- | Transfer learning in computer vision -- | Transfer learning in natural language processing -- | Transfer learning in dialogue systems -- | Transfer learning in recommender systems -- | Transfer learning in bioinformatics -- | Transfer learning in activity recognition -- | Transfer learning in urban computing. | Includes bibliographical references (pages [336]-376) and index. | xi, 379 pages | illustrations | 24 cm
Cited by 0
2024
Cited by 0
Anwar P.P. Abdul Majeed · 2025
This edited volume explores the potential of transfer learning in advancing artificial intelligence (AI) across diverse domains. Transfer learning enables AI systems to leverage knowledge gained from one task to enhance performance in another, significantly reducing data requirements and training time while improving model efficiency. The book presents the latest approaches for implementing transfer learning in various contexts, from telecommunications and brain-computer interfaces to quantum computing applications. Readers will discover innovative techniques for domain adaptation, cross-domain knowledge transfer, and hybrid classical-quantum implementations. The text addresses critical challenges in making transfer learning more explainable, reliable, and scalable, particularly concerning privacy preservation and computational efficiency. Key topics include AI-native networks, neural network transfer learning, domain adaptation strategies, and quantum machine learning integration. Both theoretical frameworks and practical implementations are discussed, making this book valuable for researchers, practitioners, and students interested in developing more efficient and capable AI systems. The content bridges the gap between theoretical understanding and practical application, offering insights into how transfer learning can be effectively deployed in real-world scenarios. By examining transfer learning through multiple lenses, from traditional neural networks to quantum computing, this volume provides a unique perspective on the future of AI development and its potential to revolutionize various technological sectors.
Cited by 0Open access
Pranav Ajeet Nerurkar, Pratik Mungekar · OSF Preprints (OSF Preprints) · 2025
Transfer Learning
Cited by 0
Harsh Bhasin · Apress eBooks · 2024
Assume that you have been assigned the responsibility of developing an app that can classify ten new musical instruments developed recently by renowned musicians. You only have a few hundred images of these instruments. To classify these images, you decide to use GoogLeNet architecture, which has around 6.8 million parameters. If you decide to train the model using the given images, you will realize that you have an insufficient number of images. However, if you train the model using the pictures of known instruments, you might be able to train it, but it will take a lot of time and computational resources. So the challenge is to train a sufficiently complex model on a dataset that does not have a sufficient number of images, and you probably do not have GPU as well.
Cited by 1
WORLD SCIENTIFIC eBooks · 2024
Cited by 0
Osipenko, Sergey · Figshare · 2020
Here we present the source code and pre-trained models to predict retention times
Cited by 0Open access
Brandon Muller, Harith Al-Sahaf, Bing Xue et al. · Proceedings of the Genetic and Evolutionary Computation Conference Companion · 2019
In machine learning, transfer learning is concerned with utilising prior knowledge as a way to improve the process of training a new model in a different, but related, domain. Transfer learning has been shown to be beneficial across a large set of problems. One of the main questions any transfer learning approach must address is "What to transfer?". This paper proposes a new transfer learning method in genetic programming (GP) to improve solving symbolic regression problems by extracting all potentially good and unique building blocks from a source problem. The proposed method is compared against standard GP and a state-of-the-art GP method on ten regression datasets. The experimental results show that the proposed method has achieved significantly better or comparable performance to that of the competitive methods. Furthermore, the proposed method shows better initial population and convergence compared to the other methods.
Cited by 15
Qiang Yang, Yu Tong Shirley Zhang, Wenyuan Dai et al. · DR-NTU (Nanyang Technological University) · 2020
This book is about the foundations, methods, techniques and applications of transfer learning. Transfer learning deals with how learning systems can quickly adapt themselves to new situations, new tasks and new environments. Transfer learning is a particularly important area of machine learning, which we can understand from several angles. First, the ability to learn from small data seems to be a particularly strong aspect of human intelligence. For example, we observe that babies learn from only a few examples and can quickly and effectively generalize from the few examples to concepts. This ability to learn from small data can be partly explained by the ability of humans to leverage and adapt the previous experience and pre-trained models to help solve future target problems. Adaptation is an innate ability of intelligent beings and artificially intelligent agents should certainly be endowed with transfer-learning ability-- | Instance-based transfer learning -- Feature-based transfer learning -- Model-based transfer learning -- Relation-based transfer learning -- Heterogeneous transfer learning -- Adversarial transfer learning -- Transfer learning in reinforcement learning -- Multi-task learning -- Transfer learning theory -- Transitive transfer learning -- AutoTL : learning to transfer automatically -- Few-shot learning -- Lifelong machine learning -- Privacy-preserving transfer learning -- Transfer learning in computer vision -- Transfer learning in natural language processing -- Transfer learning in dialogue systems -- Transfer learning in recommender systems -- Transfer learning in bioinformatics -- Transfer learning in activity recognition -- Transfer learning in urban computing. | Includes bibliographical references and index. | 1 online resource (xi, 379 pages)
Cited by 0