Cantitate/Preț
Produs

Interpretability in Deep Learning

Autor Ayush Somani, Alexander Horsch, Dilip K. Prasad
en Limba Engleză Paperback – 2 mai 2024

Structura acestei lucrări urmează o traiectorie progresivă riguroasă, menită să transforme natura opacă a sistemelor de învățare profundă într-un cadru de analiză transparent și aplicabil. Observăm o tranziție metodică de la conceptele fundamentale de rețele neurale, prezentate în primele capitole, către tehnici avansate de interpretare a arhitecturilor complexe. Subliniem importanța capitolului dedicat codificării cunoștințelor (Knowledge Encoding), care oferă instrumentele necesare pentru a înțelege cum sunt reprezentate informațiile în straturile ascunse ale modelelor. Reținem că volumul nu se limitează la teorie, ci integrează studii de caz concrete din domenii precum computer vision și optică, oferind o perspectivă tehnică asupra aplicabilității cercetării recente. Abordarea diferă de Explainable Neural Networks Based on Fuzzy Logic and Multi-criteria Decision Tools de József Dombi prin faptul că este mai puțin concentrată exclusiv pe logica fuzzy și mai mult aplicabilă pe o gamă largă de arhitecturi standard de deep learning, deși include și o secțiune dedicată pentru Fuzzy Deep Learning. Spre deosebire de manualele pur teoretice, această monografie publicată de Springer servește drept resursă pentru specialiștii care au responsabilități de dezvoltare și implementare, punând accent pe instrumentele de vizualizare și interpretare care pot fi integrate în fluxurile de lucru curente. Organizarea pe 466 de pagini permite o explorare detaliată a fiecărui subiect, de la fundamente la aplicații specifice, facilitând o înțelegere profundă a mecanismelor decizionale ale inteligenței artificiale.

Citește tot Restrânge

Preț: 104841 lei

Preț vechi: 131051 lei
-20%

Puncte Express: 1573

Carte tipărită la comandă

Livrare economică 15-20 iunie


Specificații

ISBN-13: 9783031206412
ISBN-10: 303120641X
Pagini: 488
Ilustrații: XX, 466 p. 176 illus., 172 illus. in color.
Dimensiuni: 155 x 235 x 25 mm
Greutate: 0.82 kg
Ediția:2023
Editura: Springer
Locul publicării:Cham, Switzerland

De ce să citești această carte

Pentru cercetătorii și inginerii care doresc să elimine caracterul de „cutie neagră” al modelelor neurale. Această carte oferă un echilibru între rigoarea academică și studiile de caz practice, permițând cititorului să dobândească instrumente concrete pentru validarea și explicarea deciziilor luate de algoritmi de deep learning în medii de producție.


Despre autor

Ayush Somani, Alexander Horsch și Dilip K. Prasad sunt cercetători activi în domeniul inteligenței artificiale și al procesării de imagini. Alexander Horsch are o experiență vastă în informatică medicală și viziune computerizată, în timp ce Dilip K. Prasad este recunoscut pentru contribuțiile sale în ingineria sistemelor și machine learning aplicat. Expertiza lor combinată asigură o abordare multidisciplinară în Interpretability in Deep Learning, îmbinând cunoștințele de hardware optic cu algoritmi avansați de rețele neurale.


Descriere scurtă

This book is a comprehensive curation, exposition and illustrative discussion of recent research tools for interpretability of deep learning models, with a focus on neural network architectures. In addition, it includes several case studies from application-oriented articles in the fields of computer vision, optics and machine learning related topic. 
The book can be used as a monograph on interpretability in deep learning covering the most recent topics as well as a textbook for graduate students. Scientists with research, development and application responsibilities benefit from its systematic exposition.  
 

Cuprins

Chapter 1. Introduction.- Chapter 2. Neural networks for deep learning.- Chapter 3. Knowledge Encoding and Interpretation.- Chapter 4. Interpretation in Specific Deep Learning Architectures.- Chapter 5. Fuzzy Deep Learning.

Notă biografică

Ayush Somani is a research fellow in the Department of Computer Science at UiT The Arctic University of Norway. He received his Integrated Masters from Indian Institute of Technology (ISM) Dhanbad in Maths and Computing. He has earned multiple honors like Dare2Compete Awards 2021, Samsung Innovation Award 2020, KDD'20 Travel Award, and Finalist in Machine Learning & Software Development Flipkart Grid 2.0 challenge. At Travel Buddy, he worked as a data scientist intern to implement AI-automated content moderation. He has research interests in interpretability, explanability, and other aspects of deep learning.
 
Alexander Horsch, born 1955, is a full professor at the Department of Computer Science, UiT The Arctic University of Norway. He holds a Ph.D. in Computer Science (1989) and a Dr. med. habil in Medical Informatics (1999), both from the Technical University of Munich (TUM). He was the head of the Medical Computing Center at Klinikum rechts der Isar, TUM (1987–1995), and researcher and lecturer, later associate professor and APL professor at TUM Medical Faculty (1996–2015). Several research projects in telemedicine and computer-aided diagnosis with grants from the German Ministry of Research and Technology, the Bavarian State Government, the European Union, and the German Telekom have been managed by him. From beginning 2015 to summer 2019, he was the head of the Department of Computer Science at UiT. He is a member of the research group for physical activity at UiT Medical Faculty, focusing on sensor data analysis within the Tromsø Study, a large epidemiological trial. He is the principal investigator of the interdisciplinary project VirtualStain (2020–2024) at UiT. Earlier, he has worked with the European Space Agency (ESA) since 2004 when he was a member of the ESA Telemed Working Group and with the World Health Organization (WHO) since 2005 as an eHealth and telemedicine expert. From 2006, he has worked in different periods as a consultant for EC (Telemedicine Task Force) and ESA in the Satellite-Enhanced eHealth for sub-Saharan Africa (eHSA) program. Since 2011, he was also supporting the United Nations Office for Outer Space Affairs (UNOOSA) in its Human Space Technology Initiative (HSTI). He is author or co-author of numerous scientific publications and has supervised a dozen doctoral students. His professional expertise ranges from eHealth applications to medical decision support. He has led or was a partner in projects for teleservices in gastroenterology and other medical specialties, web-based multi-modal interactive teaching of tumor diagnostics, case-based ophthalmologic eLearning, early detection of malignant melanoma, quantitative measurement of tumors using tomography data, and accelerometry for physical activity measurements in population studies and clinical research. His current scientific focus is on data analytics applied to biosensor time series and biological images using classical and machine learning approaches.  
Dilip K. Prasad is an associate professor in the Department of Computer Science at UiT The Arctic University of Norway. He received the Ph.D. from Nanyang Technological University, Singapore and B.Tech. degree in Computer Science and Engineering from Indian Institute of Technology (ISM) Dhanbad, India. He was a senior research fellow at Nanyang Technological University, Singapore and research fellow at National University of Singapore. He has 5years of industrial experience with IBM, Infosys, Mediatek and Philips. He was a Kauffman Global Scholarship fellow in 2011. He has received 'Rolls-Royce Inventor Award' and several research grants from European Union, Research Council Norway and UiT The Arctic University of Norway. He is a founding member of Bio-AI Research Group at UiT The Arctic University of Norway.  His research interests include image processing, pattern recognition, computer vision and artificial intelligence. He is passionate about making artificial intelligence interpretable and scalable toward bridging the intelligence gap between human and machines.
 


Caracteristici

Presents full coverage of interpretability in deep learning Explains the fundamental concepts of interpretability and the state of the art on the topic Includes fuzzy deep learning architectures