Optimization Techniques for Deep Learning: Improving Performance and Efficiency: 238 - Rilegato

Hemmati, Atefeh; Rahmani, Amir Masoud; Bazikar, Fatemeh; Moosaei, Hossein; Pardalos, Panos M.

Rilegato

ISBN 10: 3032207029 ISBN 13: 9783032207029

Casa editrice: Springer-Verlag GmbH, 2026

Riassunto

This book offers a comprehensive guide to optimization techniques in deep learning, a transformative branch of artificial intelligence that has revolutionized fields from computer vision to healthcare. By bridging the gap between theoretical concepts and practical applications, it equips readers with the tools needed to harness the full potential of deep neural networks.

The chapters cover a wide range of optimization methods, beginning with the fundamentals of neural networks and key concepts of deep learning. Readers will explore critical topics such as gradient descent, stochastic optimization, and advanced algorithms, while also addressing the inherent challenges of optimization. The book delves into practical aspects, offering insights into how to make training deep models more efficient and stable. Emerging trends and future perspectives are also presented, making this work a must-read for anyone looking to stay at the forefront of the field.

This book is an invaluable resource for researchers and practitioners seeking practical solutions for optimizing neural networks. Students will find a clear path to understanding the principles and building theoretical knowledge, while industry professionals will gain insights into the latest techniques and trends. Whether you're a seasoned expert or new to the field, this book is essential for anyone interested in deep learning optimization.

Su questo libro

Informazioni sull'autore

Atefeh Hemmati received her B.S. degree in Computer Engineering, Information Technology from Central Tehran Branch, IAU, Tehran, Iran in 2020 and received her M.S. degree in Computer Engineering, Software from the Science and Research Branch, IAU, Tehran, Iran in 2023. Her research interests include Internet of Things, LLMs, fog/cloud/edge computing, and artificial intelligence, especially in the fields of machine learning, deep learning. She has authored several publications in these fields

and actively contributes to advanced AI applications in IoT ecosystems.

 

Amir Masoud Rahmani received his B.S. in computer engineering from Amir Kabir University, Tehran, in 1996, his M.S. in computer engineering from Sharif University of Technology, Tehran, in 1998, and his Ph.D. in computer engineering from IAU University, Tehran, in 2005. Currently, he is a professor of computer engineering. His research interests include Machine Learning, the Internet of Things, cloud/fog computing, and artificial intelligence.

 

Fatemeh Bazikar received her B.S. degree in Applied Mathematics, Shahid Chamran University, Ahvaz, Iran, in 2011, her M.S. in Applied Mathematics (Optimization), Shahid Chamran University, Ahvaz, Iran, in 2013, her Ph.D. in Applied Mathematics, Guilan University, Rasht, Iran, in 2021, and her Postdoc Researcher in Department of Computer Science, Faculty of Mathematical Sciences, Alzahra University, Tehran, Iran, in 2024. Her research interests include Machine Learning, Optimization, Data Analysis, Mathematical Programming, and artificial intelligence, especially in the fields of machine learning.

 

Hossein Moosaei is an Associate Professor specializing in optimization, machine learning, and applied mathematics. He received his PhD in Applied Mathematics in 2013. His research spans optimization, machine learning, numerical analysis, biomedical applications, and scientific computing. He has authored over 60 publications in these fields and serves as a reviewer, guest editor, and editor for leading international journals. In addition, he has played a key role in organizing international conferences, contributing to the advancement of the global research community.

 

Panos Pardalos is a Distinguished Emeritus Professor in the Department of Industrial and Systems Engineering at the University of Florida, and an affiliated faculty of Biomedical Engineering and Computer Science & Information; Engineering departments. Panos Pardalos is a world-renowned leader in Global Optimization, Mathematical Modeling, Energy Systems, Financial applications, and Data Sciences. He is a Fellow of AAAS, AAIA, AIMBE, EUROPT, and INFORMS and was awarded the 2013 Constantin Caratheodory Prize of the International Society of Global Optimization. In addition, Panos Pardalos has been awarded the 2013 EURO Gold Medal prize bestowed by the Association for European Operational Research Societies. This medal is the preeminent European award given to Operations Research (OR) professionals for “scientific contributions that stand the test of time.” Panos Pardalos has been awarded a prestigious Humboldt Research Award (2018-2019). The Humboldt Research Award is granted in recognition of a researcher’s entire achievements to date –fundamental discoveries, new theories, and insights that have had a significant impact on their discipline. Panos Pardalos is also a Member of several Academies of Sciences, and he holds several honorary degrees and affiliations. He is the Founding Editor of Optimization Letters, Energy Systems, and Co-Founder of the International Journal of Global Optimization, Computational Management Science, and Springer Nature Operations Research Forum. He has published over 600 journal papers, and edited/authored over 200 books. He is one of the most cited authors and has graduated 71 PhD students so far. Details can be found at www.ise.ufl.edu/pardalosPanos Pardalos has lectured and given invited keynote addresses worldwide in countries including, Australia, Azerbaijan, Belgium, Brazil, Canada, Chile, China, Cyprus, Czech Republic, Denmark, Egypt, England, France, Finland, Germany, Greece, Holland, Hong Kong, Hungary, Iceland, Ireland, Italy, Japan, Lithuania, Mexico, Mongolia, Montenegro, New Zealand, Norway, Peru, Portugal, Russia, South Korea, Singapore, Serbia, South Africa, Spain, Sweden, Switzerland, Taiwan, Turkey, Ukraine, United Arab Emirates, and the USA.

Dalla quarta di copertina

This book offers a comprehensive guide to optimization techniques in deep learning, a transformative branch of artificial intelligence that has revolutionized fields from computer vision to healthcare. By bridging the gap between theoretical concepts and practical applications, it equips readers with the tools needed to harness the full potential of deep neural networks.

The chapters cover a wide range of optimization methods, beginning with the fundamentals of neural networks and key concepts of deep learning. Readers will explore critical topics such as gradient descent, stochastic optimization, and advanced algorithms, while also addressing the inherent challenges of optimization. The book delves into practical aspects, offering insights into how to make training deep models more efficient and stable. Emerging trends and future perspectives are also presented, making this work a must-read for anyone looking to stay at the forefront of the field.

This book is an invaluable resource for researchers and practitioners seeking practical solutions for optimizing neural networks. Students will find a clear path to understanding the principles and building theoretical knowledge, while industry professionals will gain insights into the latest techniques and trends. Whether you're a seasoned expert or new to the field, this book is essential for anyone interested in deep learning optimization.

Dettagli dell'edizione

• Editore: Springer-Verlag GmbH
• Data di pubblicazione: 2026
• Lingua: Inglese
• ISBN 10: 3032207029
• ISBN 13: 9783032207029
• Rilegatura: Copertina rigida
• Numero di pagine: 208
• Contatto del produttore: Springer Nature Customer Service Center GmbH; ProductSafety@springernature.com; ; Europaplatz 3,69115 Heidelberg, Germany; Heidelberg; 69115; Germania