Book Image

Hands-On Machine Learning with TensorFlow.js

By : Kai Sasaki
Book Image

Hands-On Machine Learning with TensorFlow.js

By: Kai Sasaki

Overview of this book

TensorFlow.js is a framework that enables you to create performant machine learning (ML) applications that run smoothly in a web browser. With this book, you will learn how to use TensorFlow.js to implement various ML models through an example-based approach. Starting with the basics, you'll understand how ML models can be built on the web. Moving on, you will get to grips with the TensorFlow.js ecosystem to develop applications more efficiently. The book will then guide you through implementing ML techniques and algorithms such as regression, clustering, fast Fourier transform (FFT), and dimensionality reduction. You will later cover the Bellman equation to solve Markov decision process (MDP) problems and understand how it is related to reinforcement learning. Finally, you will explore techniques for deploying ML-based web applications and training models with TensorFlow Core. Throughout this ML book, you'll discover useful tips and tricks that will build on your knowledge. By the end of this book, you will be equipped with the skills you need to create your own web-based ML applications and fine-tune models to achieve high performance.

Related Content you might be interested in

Current Title:

Small book image
Hands-On Machine Learning with TensorFlow.js
Kai Sasaki
Nov, 2019 | 296 pages
Small book image
Hands-On Neural Networks with TensorFlow 2.0
Paolo Galeone
Sep, 2019 | 358 pages
Small book image
Deep Learning with TensorFlow 2 and Keras
Sujit Pal | Amita Kapoor | Antonio Gulli
Dec, 2019 | 646 pages
Small book image
Machine Learning with Go Quick Start Guide
Michael Bironneau | Toby Coleman
May, 2019 | 168 pages
Table of Contents (17 chapters)
Preface
Preface
Who this book is for
What this book covers
To get the most out of this book
Get in touch
Free Chapter
1
Section 1: The Rationale of Machine Learning and the Usage of TensorFlow.js
Section 1: The Rationale of Machine Learning and the Usage of TensorFlow.js
2
Machine Learning for the Web
Machine Learning for the Web
Technical requirements
Why machine learning on the web?
Operation graphs
What is TensorFlow.js?
Installing TensorFlow.js
The low-level API
The Layers API
Summary
Questions
Further reading
3
Importing Pretrained Models into TensorFlow.js
Importing Pretrained Models into TensorFlow.js
Technical requirements
The portable model format
Exporting a model from TensorFlow
Converting models using tfjs-converter
Loading the model into TensorFlow.js
Summary
Questions
Further reading
4
TensorFlow.js Ecosystem
TensorFlow.js Ecosystem
Technical requirements
Why high-level libraries?
Using existing models
Loading the data from various kinds of storage
Pose detection with ML5.js
Drawing cats with Magenta.js
XOR classification with machinelearn.js
Summary
Exercises
Further reading
5
Section 2: Real-World Applications of TensorFlow.js
Section 2: Real-World Applications of TensorFlow.js
6
Polynomial Regression
Polynomial Regression
Technical requirements
What is polynomial regression?
Two-dimensional curve fitting
Summary
Questions
Further reading
7
Classification with Logistic Regression
Classification with Logistic Regression
Technical requirements
Background of binary classification
What is logistic regression?
Classifying two-dimensional clusters
Summary
Questions
Further reading
8
Unsupervised Learning
Unsupervised Learning
Technical requirements
What is unsupervised learning?
Learning how K-means works
Generalizing K-means with the EM algorithm
Clustering two groups in a 2D space
Summary
Exercise
Further reading
9
Sequential Data Analysis
Sequential Data Analysis
Technical requirements
What is Fourier transformation?
Cosine curve decomposition
Summary
Exercise
Further reading
10
Dimensionality Reduction
Dimensionality Reduction
Technical requirements
Why dimensionality reduction?
Understanding principal component analysis
Projecting 3D points into a 2D space with PCA
Word embedding
Summary
Exercise
Further reading
11
Solving the Markov Decision Process
Solving the Markov Decision Process
Technical requirements
Reinforcement learning
Solving the four-states environment
Summary
Exercise
Further reading
12
Section 3: Productionizing Machine Learning Applications with TensorFlow.js
Section 3: Productionizing Machine Learning Applications with TensorFlow.js
13
Deploying Machine Learning Applications
Deploying Machine Learning Applications
Technical requirements
The ecosystem around the JavaScript platform
Module bundler
Deploying modules with GitHub Pages
Summary
Questions
Further reading
14
Tuning Applications to Achieve High Performance
Tuning Applications to Achieve High Performance
Technical requirements
The backend API of TensorFlow.js
Tensor management
Asynchronous data access
Profiling
Model visualization
Summary
Questions
Further reading
15
Future Work Around TensorFlow.js
Future Work Around TensorFlow.js
Technical requirements
Experimental backend implementations
AutoML edge helper
Summary
Questions
Further Reading
16
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think

Background of binary classification

Classification is a type of supervised learning. We need a machine learning model in order to predict the correct label for a new instance. For example, the handwritten image recognition problem is categorized as a classification problem. The most popular dataset for handwritten digits is MNIST. MNIST was developed by Yann LeCun, who won the Turing award in 2018 for leading the current boom of artificial intelligence research. This is the prediction result when using TensorFlow.js:

While handwritten digit classification is a multi-label classification problem, the problem we are going to solve in this chapter is binary classification. The target labels to be predicted in the binary classification situation have only two labels: positive and negative. In the following example, there are two classes: a set of rhombuses and circles. If these two...

Previous Section
End of Section 3
Next Section