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
Hands-On Machine Learning with TensorFlow.js

You're reading from   Hands-On Machine Learning with TensorFlow.js A guide to building ML applications integrated with web technology using the TensorFlow.js library

Arrow left icon
Product type Paperback
Published in Nov 2019
Publisher Packt
ISBN-13 9781838821739
Length 296 pages
Edition 1st Edition
Languages
Arrow right icon
Author (1):
Arrow left icon
Kai Sasaki Kai Sasaki
Author Profile Icon Kai Sasaki
Kai Sasaki
Arrow right icon
View More author details
Toc

Table of Contents (17) Chapters Close

Preface 1. Section 1: The Rationale of Machine Learning and the Usage of TensorFlow.js
2. Machine Learning for the Web FREE CHAPTER 3. Importing Pretrained Models into TensorFlow.js 4. TensorFlow.js Ecosystem 5. Section 2: Real-World Applications of TensorFlow.js
6. Polynomial Regression 7. Classification with Logistic Regression 8. Unsupervised Learning 9. Sequential Data Analysis 10. Dimensionality Reduction 11. Solving the Markov Decision Process 12. Section 3: Productionizing Machine Learning Applications with TensorFlow.js
13. Deploying Machine Learning Applications 14. Tuning Applications to Achieve High Performance 15. Future Work Around TensorFlow.js 16. Other Books You May Enjoy

Summary

In this chapter, we have introduced several machine learning frameworks running on the web. Since tfjs-models and Magenta.js are mainly developed by the same community as TensorFlow.js, they can be naturally integrated with TensorFlow. These libraries contain many state-of-the-art machine learning models and even include pre-trained model parameters. While tfjs-models contain various kinds of models for general purposes, Magenta.js is for more artistic applications. You will be able to find the appropriate machine learning model for your application type.

On the other hand, ML5.js and machinelearn.js are higher-level libraries. They provide tools and workflows that are indispensable for building common pipelines to train machine learning models such as preprocessing and dimensionality reduction. In addition to that, their usage and interface are similar to popular libraries...

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 $19.99/month. Cancel anytime