Front cover image for Linear algebra and learning from data

Linear algebra and learning from data

Gilbert Strang (Author)
"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 (column-row) 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 large-scale 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." -- Publisher's description
Print Book, English, 2019
Wellesley-Cambridge Press, Wellesley, MA, 2019
Textbooks
xiii, 432 pages : illustrations ; 25 cm
9780692196380, 0692196382
1081372892
Deep learning and neural nets
Preface and acknowledgements
Part I: Highlights of linear algebra
Part II: Computations with large matrices
Part III: Low rank and compressed sensing
Part IV: Special matrices
Part V: Probability and statistics
Part IV: Optimization
Part VII: Learning from data
Books on machine learning
Image compression by the SVD
Codes and algorithms for numerical linear algebra
Counting parameters in the basic factorizations
Index of authors
Index
Index of symbols