Cantitate/Preț
Produs

Deep Learning

Autor Christopher M. Bishop, Hugh Bishop
en Limba Engleză Hardback – 2 noi 2023

În domeniul inteligenței artificiale, unde ritmul inovației depășește adesea capacitatea de documentare, lucrarea Deep Learning semnată de Christopher M. Bishop și Hugh Bishop apare ca un pilon de stabilitate. Descoperim aici o abordare care prioritizează principiile fundamentale menite să reziste probei timpului, fără a neglija însă arhitecturile contemporane care definesc prezentul. Cartea este organizată meticulos în capitole concise, cu o progresie liniară ce pornește de la fundamentele matematice — incluzând o introducere autonomă în teoria probabilităților — și avansează spre rețele neuronale profunde, mecanisme de Backpropagation și tehnici de regularizare. Reținem capacitatea autorilor de a demistifica subiecte complexe prin utilizarea unor perspective multiple: de la diagrame intuitive și descrieri narative, până la rigoarea formulelor matematice și a pseudo-codului aplicabil. Ca și Simon J. D. Prince în Understanding Deep Learning, autorii distilează experiență reală în principii acționabile, oferind acel echilibru necesar între teorie și valoarea practică în lumea reală. Această lucrare reprezintă o evoluție firească în opera lui Christopher M. Bishop; dacă în Neural Networks for Pattern Recognition punea bazele rețelelor feed-forward din perspectivă statistică, noul volum integrează revoluția ultimilor ani, acoperind modele Transformer, Graph Neural Networks și modele de difuzie. Structura editorială facilitează atât studiul individual, cât și parcurgerea unui curs academic de două semestre, acoperind inclusiv teme avansate precum variabilele latente și rețelele generative adversariale (GAN). Credem că rigoarea specifică editurii Springer Verlag GmbH se îmbină perfect cu viziunea pragmatică a autorilor, rezultând într-un instrument esențial pentru oricine dorește să înțeleagă arhitectura sistemelor AI moderne.

Citește tot Restrânge

Preț: 50844 lei

Preț vechi: 63554 lei
-20%

Puncte Express: 763

Carte disponibilă

Livrare economică 05-19 mai
Livrare express 21-25 aprilie pentru 8154 lei


Specificații

ISBN-13: 9783031454677
ISBN-10: 3031454677
Pagini: 649
Ilustrații: XX, 649 p. 600 illus., 400 illus. in color.
Dimensiuni: 185 x 260 x 32 mm
Greutate: 1.66 kg
Ediția:2024
Editura: Springer Verlag GmbH
Locul publicării:Cham, Switzerland

De ce să citești această carte

Această carte este recomandată atât profesioniștilor care doresc să își consolideze baza teoretică, cât și studenților la informatică. Cititorul câștigă o înțelegere profundă a modelelor care motorizează sistemele AI actuale, beneficiind de expertiza unor autori care activează la vârful cercetării (Microsoft și Wayve). Este resursa ideală pentru a trece de la utilizarea unor biblioteci software la proiectarea și antrenarea propriilor rețele neuronale complexe.


Despre autor

Christopher M. Bishop este Technical Fellow la Microsoft și Director al Microsoft Research AI4Science, fiind recunoscut la nivel mondial pentru contribuțiile sale în învățarea automată. Este membru al Royal Academy of Engineering și al Royal Society, având o experiență vastă în explicarea conceptelor complexe prin lucrări de referință precum Pattern Recognition and Machine Learning. Hugh Bishop este Applied Scientist la Wayve, unde proiectează rețele neuronale pentru conducere autonomă, aducând volumului o perspectivă aplicată, ancorată în provocările tehnice ale industriei de profil.


Cuprins

Preface.- The Deep Learning Revolution.- Probabilities.- Standard Distributions.- Single-layer Networks: Regression.- Single-layer Networks: Classification.- Deep Neural Networks.- Gradient Descent.- Backpropagation.- Regularization.- Convolutional Networks.- Structured Distributions.- Transformers.- Graph Neural Networks.- Sampling.- Discrete Latent Variables.- Continuous Latent Variables.- Generative Adversarial Networks.- Normalizing Flows.- Autoencoders.- Diffusion Models.- Appendix A Linear Algebra.- Appendix B Calculus of Variations.- Appendix C Lagrange Multipliers.- Biblyography.- Index

Notă biografică

Chris Bishop is a Technical Fellow at Microsoft and is the Director of Microsoft Research AI4Science. He is a Fellow of Darwin College, Cambridge, a Fellow of the Royal Academy of Engineering, a Fellow of the Royal Society of Edinburgh, and a Fellow of the Royal Society of London. He is a keen advocate of public engagement in science, and in 2008 he delivered the prestigious Royal Institution Christmas Lectures, established in 1825 by Michael Faraday, and broadcast on prime-time national television. Chris was a founding member of the UK AI Council and was also appointed to the Prime Minister’s Council for Science and Technology.
Hugh Bishop is an Applied Scientist at Wayve, an end-to-end deep learning based autonomous driving company in London, where he designs and trains deep neural networks. Before working at Wayve, he completed his MPhil in Machine Learning and Machine Intelligence in the engineering department at Cambridge University. Hugh also holds an MEng in Computer Science from the University of Durham, where he focused his projects on deep learning. During his studies, he also worked as an intern at FiveAI, another autonomous driving company in the UK, and as a Research Assistant, producing educational interactive iPython notebooks for machine learning courses at Cambridge University.


Textul de pe ultima copertă

This book offers a comprehensive introduction to the central ideas that underpin deep learning. It is intended both for newcomers to machine learning and for those already experienced in the field. Covering key concepts relating to contemporary architectures and techniques, this essential book equips readers with a robust foundation for potential future specialization. The field of deep learning is undergoing rapid evolution, and therefore this book focusses on ideas that are likely to endure the test of time.
The book is organized into numerous bite-sized chapters, each exploring a distinct topic, and the narrative follows a linear progression, with each chapter building upon content from its predecessors. This structure is well-suited to teaching a two-semester undergraduate or postgraduate machine learning course, while remaining equally relevant to those engaged in active research or in self-study.

A full understanding of machine learning requires some mathematical background and so the book includes a self-contained introduction to probability theory. However, the focus of the book is on conveying a clear understanding of ideas, with emphasis on the real-world practical value of techniques rather than on abstract theory. Complex concepts are therefore presented from multiple complementary perspectives including textual descriptions, diagrams, mathematical formulae, and pseudo-code.

Chris Bishop is a Technical Fellow at Microsoft and is the Director of Microsoft Research AI4Science. He is a Fellow of Darwin College Cambridge, a Fellow of the Royal Academy of Engineering, and a Fellow of the Royal Society. 

Hugh Bishop is an Applied Scientist at Wayve, a deep learning autonomous driving company in London, where he designs and trains deep neural networks. He completed his MPhil in Machine Learning and Machine Intelligence at Cambridge University.

“Chris Bishop wrote a terrific textbook on neural networks in 1995 and has a deep knowledge of the field and its core ideas. His many years of experience in explaining neural networks have made him extremely skillful at presenting complicated ideas in the simplest possible way and it is a delight to see these skills applied to the revolutionary new developments in the field.” -- Geoffrey Hinton
"With the recent explosion of deep learning and AI as a research topic, and the quickly growing importance of AI applications, a modern textbook on the topic was badly needed. The "New Bishop" masterfully fills the gap, covering algorithms for supervised and unsupervised learning, modern deep learning architecture families, as well as how to apply all of this to various application areas." – Yann LeCun

“This excellent and very educational book will bring the reader up to date with the main concepts and advances in deep learning with a solid anchoring inprobability. These concepts are powering current industrial AI systems and are likely to form the basis of further advances towards artificial general intelligence.” --  Yoshua Bengio



Caracteristici

Foundational and conceptual approach emphasizes real-world practical value of techniques for a wide range of learners Companion volume to the author's standard reference text Pattern Recognition and Machine Learning To reinforce key ideas, end-of-chapter exercises of varying difficulty are included to promote active learning