Hardcover ISBN: | 978-0-692-19638-0 |
Product Code: | STRANG/3 |
List Price: | $95.00 |
AMS Member Price: | $76.00 |
Hardcover ISBN: | 978-0-692-19638-0 |
Product Code: | STRANG/3 |
List Price: | $95.00 |
AMS Member Price: | $76.00 |
-
Book DetailsThe Gilbert Strang SeriesVolume: 3; 2019; 432 ppMSC: Primary 15; Secondary 68
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.
A publication of Wellesley-Cambridge Press. Distributed within the Americas by the American Mathematical Society.
ReadershipAnyone interested in learning how data is reduced and interpreted by matrix methods.
-
Additional Material
-
RequestsReview Copy – for publishers of book reviewsDesk Copy – for instructors who have adopted an AMS textbook for a courseExamination Copy – for faculty considering an AMS textbook for a courseAccessibility – to request an alternate format of an AMS title
- Book Details
- Additional Material
- Requests
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.
A publication of Wellesley-Cambridge Press. Distributed within the Americas by the American Mathematical Society.
Anyone interested in learning how data is reduced and interpreted by matrix methods.