Cantitate/Preț
Produs
Total produse
Vezi coșul
Neural Networks and Deep Learning de Charu C. Aggarwal

Neural Networks and Deep Learning

Autor Charu C. Aggarwal
en Limba Engleză Paperback – iul 2024

În cadrul acestei a doua ediții a volumului Neural Networks and Deep Learning, descoperim o structură riguros compartimentată, menită să ghideze cititorul de la mecanismele elementare la cele mai complexe arhitecturi contemporane. Organizarea materialului urmează o progresie logică în trei etape: primele capitole stabilesc legătura matematică dintre învățarea automată clasică și rețelele neuronale, partea centrală se concentrează pe fundamentele antrenării și regularizării, în timp ce secțiunile finale explorează frontierele actuale ale domeniului. Reținem efortul autorului de a demistifica succesul rețelelor adânci, oferind răspunsuri argumentate la întrebări esențiale despre utilitatea adâncimii rețelelor și dificultățile inerente procesului de antrenare. Considerăm că această ediție aduce o valoare adăugată semnificativă prin capitolele noi despre rețelele neuronale pe grafuri și prin extinderea secțiunilor dedicate modelelor de limbaj bazate pe transformatoare. Această abordare completează perspectiva oferită de Understanding Deep Learning de Simon J. D. Prince; în timp ce Prince pune accent pe o intuiție digestibilă și curatată, Charu C. Aggarwal preferă o tratare algoritmică exhaustivă, ancorată în teoria matematică solidă. De asemenea, lucrarea se distinge de Introduction to Deep Learning de Sandro Skansi prin profunzimea detaliilor tehnice, fiind adresată cu precădere studenților la nivel masteral sau cercetătorilor. Poziționăm acest titlu ca un pilon central în opera autorului, făcând trecerea de la lucrările sale axate pe baze de date spre inteligența artificială modernă. Cartea rafinează conceptele prezentate în Linear Algebra and Optimization for Machine Learning, aplicând acele fundamente teoretice direct în designul arhitectural al rețelelor neuronale. Prin includerea unor teme precum învățarea prin întărire (reinforcement learning) și rețelele generative adversariale, Aggarwal oferă un instrumentar complet pentru înțelegerea peisajului tehnologic actual.

Citește tot Restrânge

Preț: 42705 lei

Puncte Express: 641
Paperback (2) de la 33655 lei
Hardback 46925 lei

Carte disponibilă

Livrare economică 19 mai-02 iunie
Livrare express 02-08 mai pentru 6462 lei

 Adaugă în coș

Wish list
Gift list
Am citit!
Adaugă în listă

Specificații

ISBN-13: 9783031296444
ISBN-10: 3031296443
Pagini: 556
Ilustrații: XXIV, 529 p. 150 illus., 22 illus. in color.
Dimensiuni: 178 x 254 x 30 mm
Greutate: 1.03 kg
Ediția:Second Edition 2023
Editura: Springer
Locul publicării:Cham, Switzerland

De ce să citești această carte

Recomandăm această carte oricărui student la informatică sau inginerie care dorește să înțeleagă nu doar cum să folosească modelele de deep learning, ci mai ales de ce funcționează acestea. Cititorul câștigă o viziune unitară asupra domeniului, învățând să proiecteze arhitecturi specifice pentru text, imagini sau grafuri. Este resursa ideală pentru a trece de la utilizarea unor biblioteci software la înțelegerea algoritmilor de bază care stau la temelia inteligenței artificiale.

Despre autor

Charu C. Aggarwal este un cercetător de renume mondial, ocupând poziția de Research Staff Member la IBM Research. Cu un parcurs academic de excepție, fiind licențiat la IIT Kanpur și doctor al MIT, Aggarwal a publicat peste 90 de lucrări științifice și deține zeci de brevete de invenție, fiind desemnat „Master Inventor” de către IBM. Experiența sa vastă în data mining și baze de date se reflectă în precizia matematică a textelor sale. În contextul actualei lucrări, autorul folosește rigoarea dobândită în cercetarea industrială pentru a oferi o perspectivă pragmatică, dar profund teoretică asupra rețelelor neuronale.

Descriere scurtă

This book covers both classical and modern models in deep learning. The primary focus is on the theory and algorithms of deep learning. The theory and algorithms of neural networks are particularly important for understanding important concepts, so that one can understand the important design concepts of neural architectures in different applications. Why do neural networks work? When do they work better than off-the-shelf machine-learning models? When is depth useful? Why is training neural networks so hard? What are the pitfalls? The book is also rich in discussing different applications in order to give the practitioner a flavor of how neural architectures are designed for different types of problems. Deep learning methods for various data domains, such as text, images, and graphs are presented in detail. The chapters of this book span three categories:
  The basics of neural networks: The backpropagation algorithm is discussed in Chapter 2.
Many traditional machine learning models can be understood as special cases of neural networks. Chapter 3 explores the connections between traditional machine learning and neural networks. Support vector machines, linear/logistic regression, singular value decomposition, matrix factorization, and recommender systems are shown to be special cases of neural networks.
 
Fundamentals of neural networks:  A detailed discussion of training and regularization is provided in Chapters 4 and 5. Chapters 6 and 7 present radial-basis function (RBF) networks and restricted Boltzmann machines.
  Advanced topics in neural networks:  Chapters 8, 9, and 10 discuss recurrent neural networks, convolutional neural networks, and graph neural networks. Several advanced topics like deep reinforcement learning, attention mechanisms, transformer networks, Kohonen self-organizing maps, and generative adversarial networks are introduced in Chapters 11 and 12.
 
The textbook is written for graduate students and upper under graduate level students. Researchers and practitioners working within this related field will want to purchase this as well.
Where possible, an application-centric view is highlighted in order to provide an understanding of the practical uses of each class of techniques.
The second edition is substantially reorganized and expanded with separate chapters on backpropagation and graph neural networks. Many chapters have been significantly revised over the first edition. Greater focus is placed on modern deep learning ideas such as attention mechanisms, transformers, and pre-trained language models.

Cuprins

An Introduction to Neural Networks.- The Backpropagation Algorithm.- Machine Learning with Shallow Neural Networks.- Deep Learning: Principles and Training Algorithms.- Teaching a Deep Neural Network to Generalize.- Radial Basis Function Networks.- Restricted Boltzmann Machines.- Recurrent Neural Networks.- Convolutional Neural Networks.- Graph Neural Networks.- Deep Reinforcement Learning.- Advanced Topics in Deep Learning.

Notă biografică

Charu C. Aggarwal is a Distinguished Research Staff Member(DRSM) at the IBM T. J. Watson Research Center in Yorktown Heights, New York. He completed his undergraduate degree in Computer Science from the Indian Institute of Technology at Kanpur in 1993 and his Ph.D. from the Massachusetts Institute of Technology in 1996. He has worked extensively in the field of data mining. He has published more than 400 papers in refereed conferences and journals and authored over 80 patents. He is the author or editor of 20 books, including textbooks on data mining, recommender systems, and outlier analysis. Because of the commercial value of his patents, he has thrice been designated a Master Inventor at IBM. He is a recipient of an IBM Corporate Award (2003) for his work on bio-terrorist threat detection in data streams, a recipient of the IBM Outstanding Innovation Award (2008) for his scientific contributions to privacy technology, and a recipient of two IBM Outstanding Technical AchievementAwards (2009, 2015) for his work on data streams/high-dimensional data. He received the EDBT 2014 Test of Time Award for his work on condensation-based privacy-preserving data mining. He is a recipient of the IEEE ICDM Research Contributions Award (2015) and ACM SIGKDD Innovation Award, which are the two most prestigious awards for influential research contributions in the field of data mining. He is also a recipient of the W. Wallace McDowell Award, which is the highest award given solely by the IEEE Computer Society across the field of Computer Science.

He has served as the general co-chair of the IEEE Big Data Conference (2014) and as the program co-chair of the ACM CIKM Conference (2015), the IEEE ICDM Conference (2015), and the ACM KDD Conference (2016). He served as an associate editor of the IEEE Transactions on Knowledge and Data Engineering from 2004 to 2008. He is an associate editor of the IEEE Transactions on Big Data, an action editor of the DataMining and Knowledge Discovery Journal, and an associate editor of the Knowledge and Information System Journal. He has served or currently serves as the editor-in-chief of the ACM Transactions on Knowledge Discovery from Data as well as the ACM SIGKDD Explorations. He is also an editor-in-chief of ACM Books. He serves on the advisory board of the Lecture Notes on Social Networks, a publication by Springer. He has served as the vice-president of the SIAM Activity Group on Data Mining and is a member of the SIAM industry committee. He is a fellow of the SIAM, ACM, and the IEEE, for “contributions to knowledge discovery and data mining algorithms.

Caracteristici

Simple and intuitive discussions of neural networks and deep learning Provides mathematical details without losing the reader in complexity Includes exercises and examples Discusses both traditional neural networks and recent deep learning models Request solutions manual: sn.pub/lecturer-material

Recenzii

“The book recommends itself as a stepping-stone of the research-intensive area of deep learning and a worthy continuation of the previous textbooks written by the author … . Thanks to its systematic and thorough approach complemented with the variety of resources (bibliographic and software references, exercises) neatly presented after each chapter, it is suitable for audiences of varied expertise or background.” (Irina Ioana Mohorianu, zbMATH 1402.68001, 2019)