
2019 / xvi + 432 pages / hardcover / 9780692196380 / List Price $95.00 / SIAM Member Price $66.50 / Order Code: WC16
This is a textbook to help readers understand the steps that lead to deep learning. Linear algebra comes first—especially singular values, least squares, and matrix factorizations. Often the goal is a low rank approximation A = CR (columnrow) to a large matrix of data—to see its most important part. This uses the full array of applied linear algebra, including randomization for very large matrices.
Then deep learning creates a largescale optimization problem for the weights solved by gradient descent or better stochastic gradient descent. Finally, the book develops the architectures of fully connected neural nets and of Convolutional Neural Nets (CNNs) to find patterns in data.
Audience
This book is for anyone who wants to learn how data is reduced and interpreted by matrix mthods. This is the text for the second linear algebra course 18.065 taught by Professor Strang. The 18.06 lectures on OpenCourseWare ocw.mit.edu are widely known, and the new course starts from the four fundamental subspaces and the basic factorizations of a matrix. It explains how deep learning works and it is fully accessible without the first text.
About the Author
Gilbert Strang is a Professor of Mathematics at Massachusetts Institute of Technology and an Honorary Fellow of Balliol College, Oxford University. He is also a prolific author of a dozen highly regarded textbooks and monographs. Gilbert Strang served as president of the Society for Industrial and Applied Mathematics (SIAM) from 19992000 and chaired the U.S. National Committee on Mathematics from 20032004. He won the Henrici and Su Buchin prizes at ICIAM 2007 and the Von Neumann Medal of the U.S. Association of Computational Mechanics. He is a SIAM Fellow and a member of the National Academy of Sciences.
ISBN 9780692196380