02412nam\a2200385\a\4500 57803 20260517150221.0 260517s2022 caua b 001 0 eng d 9781492082187 paperback 9789355420121 paperback UKMGB eng rda UKMGB UKMGB OCLCF BD-DhIUB 006.31 23 B9279f Buduma, Nithin, author. Fundamentals of deep learning : designing next-generation machine intelligence algorithms / Nithin Buduma, Nikhil Buduma, and Joe Papa ; with contributions by Nicholas Locascio. Second edition. New Delhi: Shroff Publishers and Distributors Pvt.Ltd., 2022 xiii, 372 pages : illustrations ; 24 cm Previous edition: published as by Nikhil Buduma with contributions by Nicholas Locascio. 2017. Includes bibliographical references and index. Fundamentals of linear algebra for deep learning -- Fundamentals of probability -- The neural network -- Training feed-forward neural networks -- Implementing neural networks in PyTorch -- Beyond gradient descent -- Convolutional neural networks -- Embedding and representation learning -- Models for sequence analysis -- Generative models -- Methods in interpretability -- Memory augmented neural networks -- Deep reinforcement learning. We're in the midst of an AI research explosion. Deep learning has unlocked superhuman perception to power our push toward creating self-driving vehicles, defeating human experts at a variety of difficult games including Go, and even generating essays with shockingly coherent prose. But deciphering these breakthroughs often takes a PhD in machine learning and mathematics. The updated second edition of this book describes the intuition behind these innovations without jargon or complexity. CSE ps REF Omni concept Artificial intelligence. Machine learning. Neural networks (Computer science) Artificial intelligence. fast Machine learning. fast Neural networks (Computer science) fast Buduma, Nikhil, author. Papa Joe, author. Locascio, Nicholas. ddc BK 57803 57977 0 0 ddc 0 1 IUBL IUBL REF 2026-05-07 PURCHASE 2449.00 2022 0 006.31 B9279f 029690 2026-05-17 15:06:01 4898.00 2026-05-07 BK 0 0 ddc 0 1 IUBL IUBL REF 2026-05-07 PURCHASE 2449.00 2022 0 006.31 B9279f 029691 2026-05-17 15:06:00 02 4898.00 2026-05-07 BK