Search icon CANCEL
Arrow left icon
Explore Products
Best Sellers
New Releases
Books
Videos
Audiobooks
Learning Hub
Conferences
Free Learning
Arrow right icon
Arrow up icon
GO TO TOP
Deep Learning with TensorFlow and Keras – 3rd edition

You're reading from   Deep Learning with TensorFlow and Keras – 3rd edition Build and deploy supervised, unsupervised, deep, and reinforcement learning models

Arrow left icon
Product type Paperback
Published in Oct 2022
Publisher Packt
ISBN-13 9781803232911
Length 698 pages
Edition 3rd Edition
Tools
Arrow right icon
Authors (3):
Arrow left icon
Sujit Pal Sujit Pal
Author Profile Icon Sujit Pal
Sujit Pal
Antonio Gulli Antonio Gulli
Author Profile Icon Antonio Gulli
Antonio Gulli
Dr. Amita Kapoor Dr. Amita Kapoor
Author Profile Icon Dr. Amita Kapoor
Dr. Amita Kapoor
Arrow right icon
View More author details
Toc

Table of Contents (23) Chapters Close

Preface 1. Neural Network Foundations with TF 2. Regression and Classification FREE CHAPTER 3. Convolutional Neural Networks 4. Word Embeddings 5. Recurrent Neural Networks 6. Transformers 7. Unsupervised Learning 8. Autoencoders 9. Generative Models 10. Self-Supervised Learning 11. Reinforcement Learning 12. Probabilistic TensorFlow 13. An Introduction to AutoML 14. The Math Behind Deep Learning 15. Tensor Processing Unit 16. Other Useful Deep Learning Libraries 17. Graph Neural Networks 18. Machine Learning Best Practices 19. TensorFlow 2 Ecosystem 20. Advanced Convolutional Neural Networks 21. Other Books You May Enjoy
22. Index

Four generations of TPUs, plus Edge TPU

As discussed, TPUs are domain-specific processors expressly optimized for matrix operations. Now, you might remember that the basic operation of matrix multiplication is a dot product between a line from one matrix and a column from the other matrix. For instance, given a matrix multiplication , computing Y[i, 0] is:

The sequential implementation of this operation is time-consuming for large matrices. A brute-force computation has a time complexity of O(n3) for n x n matrices so it’s not feasible for running large computations.

First generation TPU

The first generation TPU (TPU v1) was announced in May 2016 at Google I/O. TPU v1 [1] supports matrix multiplication using 8-bit arithmetic. TPU v1 is specialized for deep learning inference but it does not work for training. For training there is a need to perform floating-point operations, as discussed in the following paragraphs.

A key function of TPU is the “...

lock icon The rest of the chapter is locked
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 €18.99/month. Cancel anytime