Search icon
Arrow left icon
All Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Newsletters
Free Learning
Arrow right icon
Hands-On Mathematics for Deep Learning

You're reading from  Hands-On Mathematics for Deep Learning

Product type Book
Published in Jun 2020
Publisher Packt
ISBN-13 9781838647292
Pages 364 pages
Edition 1st Edition
Languages
Author (1):
Jay Dawani Jay Dawani
Profile icon Jay Dawani

Table of Contents (19) Chapters

Preface 1. Section 1: Essential Mathematics for Deep Learning
2. Linear Algebra 3. Vector Calculus 4. Probability and Statistics 5. Optimization 6. Graph Theory 7. Section 2: Essential Neural Networks
8. Linear Neural Networks 9. Feedforward Neural Networks 10. Regularization 11. Convolutional Neural Networks 12. Recurrent Neural Networks 13. Section 3: Advanced Deep Learning Concepts Simplified
14. Attention Mechanisms 15. Generative Models 16. Transfer and Meta Learning 17. Geometric Deep Learning 18. Other Books You May Enjoy

Summary

With this, we conclude our chapter on linear algebra. So far, we have learned all the fundamental concepts of linear algebra, such as matrix multiplication and factorization, that will lead you on your way to gaining a deep understanding of how deep neural networks (DNNs) work and are designed, and what it is that makes them so powerful.

In the next chapter, we will be learning about calculus and will combine it with the concepts learned earlier on in this chapter to understand vector calculus.

You have been reading a chapter from
Hands-On Mathematics for Deep Learning
Published in: Jun 2020 Publisher: Packt ISBN-13: 9781838647292
Register for a free Packt account to unlock a world of extra content!
A free Packt account unlocks extra newsletters, articles, discounted offers, and much more. Start advancing your knowledge today.
Unlock this book and the full library FREE for 7 days
Get unlimited access to 7000+ expert-authored eBooks and videos courses covering every tech area you can think of
Renews at €14.99/month. Cancel anytime}