MARC details
| 000 -LEADER |
|---|
| fixed length control field |
02156nam a22002057a 4500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION |
|---|
| control field |
20220317154808.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION |
|---|
| fixed length control field |
220317b ||||| |||| 00| 0 eng d |
| 020 ## - INTERNATIONAL STANDARD BOOK NUMBER |
|---|
| International Standard Book Number |
9780692196380 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER |
|---|
| Classification number |
512.5 |
| Item number |
STR |
| 100 ## - MAIN ENTRY--PERSONAL NAME |
|---|
| Personal name |
Strang, Gilbert |
| 245 ## - TITLE STATEMENT |
|---|
| Title |
Linear algebra and learning from data |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. |
|---|
| Place of publication, distribution, etc. |
xiii, 432 pages : |
| Name of publisher, distributor, etc. |
illustrations ; |
| Date of publication, distribution, etc. |
25 cm |
| 300 ## - PHYSICAL DESCRIPTION |
|---|
| Page number |
Wellesley, MA : |
| Other physical details |
Wellesley-Cambridge Press, |
| Dimensions |
©2019. |
| 505 ## - FORMATTED CONTENTS NOTE |
|---|
| Title |
Deep learning and neural nets --<br/> |
| -- |
Preface and acknowledgements --<br/> |
| -- |
Part I: Highlights of linear algebra --<br/> |
| -- |
Part II: Computations with large matrices --<br/> |
| -- |
Part III: Low rank and compressed sensing --<br/> |
| -- |
Part IV: Special matrices --<br/> |
| -- |
Part V: Probability and statistics --<br/> |
| -- |
Part IV: Optimization --<br/> |
| -- |
Part VII: Learning from data --<br/> |
| -- |
Books on machine learning --<br/> |
| -- |
Eigenvalues and singular values : rank one --<br/> |
| -- |
Codes and algorithms for numerical linear algebra --<br/> |
| -- |
Counting parameters in the basic factorizations -- |
| 520 ## - SUMMARY, ETC. |
|---|
| Summary, etc. |
<br/>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. Audience: This book is for anyone who wants to learn how data is reduced and interpreted by and understand matrix methods. Based on the second linear algebra course taught by Professor Strang, whose lectures on the training data are widely known, it starts from scratch (the four fundamental subspaces) and is fully accessible without the first text. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Linear Algebras |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Mathematical optimization |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM |
|---|
| Topical term or geographic name entry element |
Mathematical statistics |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) |
|---|
| Source of classification or shelving scheme |
Dewey Decimal Classification |
| Koha item type |
Books |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) |
|---|
| -- |
4869 |
| 952 ## - LOCATION AND ITEM INFORMATION (KOHA) |
|---|
| -- |
4870 |
