Linear Algebra and Learning from Data
Share this pageGilbert Strang
A publication of Wellesley-Cambridge Press
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.
Readership
Anyone interested in learning how data is reduced and interpreted by matrix methods.