Strang's “Linear Algebra and Learning from Data” is printed and available
1–10 of 24 posts
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#2It looks like this is a boiled down subset of linear algebra sufficient for deep learning? Is that a correct assessment?
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#3It looks like this is a boiled down subset of linear algebra sufficient for deep learning? Is that a correct assessment?
To some extent. Gilbert Strang is kind of a linear algebra education celebrity.
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#4It looks like this is a boiled down subset of linear algebra sufficient for deep learning? Is that a correct assessment?
Here's what the description on Amazon says:
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.
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#5Execution of a determinant. [0]
Always love it when a professor can bring in some comic relief in the midst of a very heavy math topic. The students seem to enjoy it. I am self-teaching myself background math for preparing me to the likes of PRML-Bishop, and I wholeheartedly recommend his Linear algebra course available on MIT Courseware[1] coupled with his book[2]
[0] https://www.youtube.com/watch?v=amv58LCqCMI [1] https://ocw.mit.edu/courses/mathematics/18-06-linear-algebra... [2] https://www.amazon.com/Introduction-Linear-Algebra-Gilbert-S...
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#6It looks like this is a boiled down subset of linear algebra sufficient for deep learning? Is that a correct assessment?
To some extent. Gilbert Strang is kind of a linear algebra education celebrity.
He was pretty awesome to take linear algebra from. He had this perfectly tuned "absent minded professor" persona that had people almost literally on the edge of their seats trying to help him finish his points and his sentences. I've never seen a class so engaged before or after.
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#7It looks like this is a boiled down subset of linear algebra sufficient for deep learning? Is that a correct assessment?
Looking at ToC, he explains all linear algebra topics that might trip a CS major reading DL papers.
In addition, ~40% of the book is devoted to basic probability and statistics, optimization, and neural networks.
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#8wow $100 on amazon. It it worth the money?
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#9wow $100 on amazon. It it worth the money?
If it's nearly as good as his other work, yes.
Re: Strang's “Linear Algebra and Learning from Data” is printed and available
#10Ordered my copy a few days ago after learning about it from a talk at JuliaCon[0]. It's been a decade since I took linear algebra, so I'm also reviewing Prof. Strang's basic course[1]. What an amazing teacher.
[0] https://youtu.be/gGYcSjrqbjc
[1] https://ocw.mit.edu/courses/mathematics/18-06sc-linear-algeb...