Meta-Learning Frameworks for Imaging Applications /
Meta-learning, or learning to learn, has been gaining popularity in recent years to adapt to new tasks systematically and efficiently in machine learning. In the book, Meta-Learning Frameworks for Imaging Applications, experts from the fields of machine learning and imaging come together to explore...
| Main Authors: | , , , |
|---|---|
| Format: | software, multimedia |
| Language: | eng |
| Published: |
Hershey, Pennsylvania : IGI GLOBAL,
2023
|
| Subjects: | |
| Online Access: | https://www-igi-global-com.ezproxy.utm.my/gateway/book/309095?ct=-8584716664744899273 |
| _version_ | 1824459920920018944 |
|---|---|
| author | Sharma, Ashok, 1977-, editor 319639 Sengar, Sandeep Singh, 1985-, editor 656390 Singh, Parveen, 1976-, editor 656391 IGI Global Scientific Publishing (Online service) 655412 |
| author_facet | Sharma, Ashok, 1977-, editor 319639 Sengar, Sandeep Singh, 1985-, editor 656390 Singh, Parveen, 1976-, editor 656391 IGI Global Scientific Publishing (Online service) 655412 |
| author_sort | Sharma, Ashok, 1977-, editor 319639 |
| collection | OCEAN |
| description | Meta-learning, or learning to learn, has been gaining popularity in recent years to adapt to new tasks systematically and efficiently in machine learning. In the book, Meta-Learning Frameworks for Imaging Applications, experts from the fields of machine learning and imaging come together to explore the current state of meta-learning and its application to medical imaging and health informatics. The book presents an overview of the meta-learning framework, including common versions such as model-agnostic learning, memory augmentation, prototype networks, and learning to optimize. It also discusses how meta-learning can be applied to address fundamental limitations of deep neural networks, such as high data demand, computationally expensive training, and limited ability for task transfer. One critical topic in imaging is image segmentation, and the book explores how a meta-learning-based framework can help identify the best image segmentation algorithm, which would be particularly beneficial in the healthcare domain. This book is relevant to healthcare institutes, e-commerce companies, and educational institutions, as well as professionals and practitioners in the intelligent system, computational data science, network applications, and biomedical applications fields. It is also useful for domain developers and project managers from diagnostic and pharmacy companies involved in the development of medical expert systems. Additionally, graduate and master students in intelligent systems, big data management, computational intelligent approaches, computer vision, and biomedical science can use this book for their final projects and specific courses. |
| first_indexed | 2024-09-23T23:45:19Z |
| format | software, multimedia |
| id | KOHA-OAI-TEST:612001 |
| institution | Universiti Teknologi Malaysia - OCEAN |
| language | eng |
| last_indexed | 2025-02-19T04:49:27Z |
| publishDate | 2023 |
| publisher | Hershey, Pennsylvania : IGI GLOBAL, |
| record_format | dspace |
| spelling | KOHA-OAI-TEST:6120012025-02-14T07:16:05ZMeta-Learning Frameworks for Imaging Applications / Sharma, Ashok, 1977-, editor 319639 Sengar, Sandeep Singh, 1985-, editor 656390 Singh, Parveen, 1976-, editor 656391 IGI Global Scientific Publishing (Online service) 655412 software, multimedia Electronic books 631902 Hershey, Pennsylvania : IGI GLOBAL,2023©2023engMeta-learning, or learning to learn, has been gaining popularity in recent years to adapt to new tasks systematically and efficiently in machine learning. In the book, Meta-Learning Frameworks for Imaging Applications, experts from the fields of machine learning and imaging come together to explore the current state of meta-learning and its application to medical imaging and health informatics. The book presents an overview of the meta-learning framework, including common versions such as model-agnostic learning, memory augmentation, prototype networks, and learning to optimize. It also discusses how meta-learning can be applied to address fundamental limitations of deep neural networks, such as high data demand, computationally expensive training, and limited ability for task transfer. One critical topic in imaging is image segmentation, and the book explores how a meta-learning-based framework can help identify the best image segmentation algorithm, which would be particularly beneficial in the healthcare domain. This book is relevant to healthcare institutes, e-commerce companies, and educational institutions, as well as professionals and practitioners in the intelligent system, computational data science, network applications, and biomedical applications fields. It is also useful for domain developers and project managers from diagnostic and pharmacy companies involved in the development of medical expert systems. Additionally, graduate and master students in intelligent systems, big data management, computational intelligent approaches, computer vision, and biomedical science can use this book for their final projects and specific courses.Includes bibliographical references and index.Meta-learning, or learning to learn, has been gaining popularity in recent years to adapt to new tasks systematically and efficiently in machine learning. In the book, Meta-Learning Frameworks for Imaging Applications, experts from the fields of machine learning and imaging come together to explore the current state of meta-learning and its application to medical imaging and health informatics. The book presents an overview of the meta-learning framework, including common versions such as model-agnostic learning, memory augmentation, prototype networks, and learning to optimize. It also discusses how meta-learning can be applied to address fundamental limitations of deep neural networks, such as high data demand, computationally expensive training, and limited ability for task transfer. One critical topic in imaging is image segmentation, and the book explores how a meta-learning-based framework can help identify the best image segmentation algorithm, which would be particularly beneficial in the healthcare domain. This book is relevant to healthcare institutes, e-commerce companies, and educational institutions, as well as professionals and practitioners in the intelligent system, computational data science, network applications, and biomedical applications fields. It is also useful for domain developers and project managers from diagnostic and pharmacy companies involved in the development of medical expert systems. Additionally, graduate and master students in intelligent systems, big data management, computational intelligent approaches, computer vision, and biomedical science can use this book for their final projects and specific courses.Diagnostic imagingMachine learningDeep learning (Machine learning)https://www-igi-global-com.ezproxy.utm.my/gateway/book/309095?ct=-8584716664744899273URN:ISBN:9781668476611 |
| spellingShingle | Diagnostic imaging Machine learning Deep learning (Machine learning) Sharma, Ashok, 1977-, editor 319639 Sengar, Sandeep Singh, 1985-, editor 656390 Singh, Parveen, 1976-, editor 656391 IGI Global Scientific Publishing (Online service) 655412 Meta-Learning Frameworks for Imaging Applications / |
| title | Meta-Learning Frameworks for Imaging Applications / |
| title_full | Meta-Learning Frameworks for Imaging Applications / |
| title_fullStr | Meta-Learning Frameworks for Imaging Applications / |
| title_full_unstemmed | Meta-Learning Frameworks for Imaging Applications / |
| title_short | Meta-Learning Frameworks for Imaging Applications / |
| title_sort | meta learning frameworks for imaging applications |
| topic | Diagnostic imaging Machine learning Deep learning (Machine learning) |
| url | https://www-igi-global-com.ezproxy.utm.my/gateway/book/309095?ct=-8584716664744899273 |
| work_keys_str_mv | AT sharmaashok1977editor319639 metalearningframeworksforimagingapplications AT sengarsandeepsingh1985editor656390 metalearningframeworksforimagingapplications AT singhparveen1976editor656391 metalearningframeworksforimagingapplications AT igiglobalscientificpublishingonlineservice655412 metalearningframeworksforimagingapplications |