Book Image

TensorFlow Machine Learning Projects

By : Ankit Jain, Amita Kapoor
Book Image

TensorFlow Machine Learning Projects

By: Ankit Jain, Amita Kapoor

Overview of this book

TensorFlow has transformed the way machine learning is perceived. TensorFlow Machine Learning Projects teaches you how to exploit the benefits—simplicity, efficiency, and flexibility—of using TensorFlow in various real-world projects. With the help of this book, you’ll not only learn how to build advanced projects using different datasets but also be able to tackle common challenges using a range of libraries from the TensorFlow ecosystem. To start with, you’ll get to grips with using TensorFlow for machine learning projects; you’ll explore a wide range of projects using TensorForest and TensorBoard for detecting exoplanets, TensorFlow.js for sentiment analysis, and TensorFlow Lite for digit classification. As you make your way through the book, you’ll build projects in various real-world domains, incorporating natural language processing (NLP), the Gaussian process, autoencoders, recommender systems, and Bayesian neural networks, along with trending areas such as Generative Adversarial Networks (GANs), capsule networks, and reinforcement learning. You’ll learn how to use the TensorFlow on Spark API and GPU-accelerated computing with TensorFlow to detect objects, followed by how to train and develop a recurrent neural network (RNN) model to generate book scripts. By the end of this book, you’ll have gained the required expertise to build full-fledged machine learning projects at work.

Related Content you might be interested in

Current Title:

Small book image
TensorFlow Machine Learning Projects
Ankit Jain | Amita Kapoor
Nov, 2018 | 322 pages
Small book image
TensorFlow 1.x Deep Learning Cookbook
Amita Kapoor | Antonio Gulli
Dec, 2017 | 536 pages
Small book image
Hands-On Deep Learning Algorithms with Python
Sudharsan Ravichandiran
Jul, 2019 | 512 pages
Small book image
Hands-On Deep Learning Architectures with Python
Yuxi Hayden Liu | Saransh Mehta
Apr, 2019 | 316 pages
Table of Contents (23 chapters)
Title Page
Title Page
Copyright and Credits
Copyright and Credits
Dedication
Dedication
About Packt
About Packt
Contributors
Contributors
Preface
Preface
Free Chapter
1
Overview of TensorFlow and Machine Learning
Overview of TensorFlow and Machine Learning
What is TensorFlow?
The TensorFlow core
Computation graph
Machine learning, classification, and logistic regression
Logistic regression with TensorFlow
Logistic regression with Keras
Summary
Questions
Further reading
2
Using Machine Learning to Detect Exoplanets in Outer Space
Using Machine Learning to Detect Exoplanets in Outer Space
What is a decision tree?
Why do we need ensembles?
Decision tree-based ensemble methods
Decision tree-based ensembles in TensorFlow
Detecting exoplanets in outer space
Building a TFBT model for exoplanet detection
Summary
Questions
Further reading
3
Sentiment Analysis in Your Browser Using TensorFlow.js
Sentiment Analysis in Your Browser Using TensorFlow.js
Understanding TensorFlow.js
Understanding Adam Optimization
Understanding categorical cross entropy loss
Understanding word embeddings
Building the sentiment analysis model
Running the model on a browser using TensorFlow.js
Summary
Questions
4
Digit Classification Using TensorFlow Lite
Digit Classification Using TensorFlow Lite
What is TensorFlow Lite?
Classification Model Evaluation Metrics
Classifying digits using TensorFlow Lite
Summary
Questions
5
Speech to Text and Topic Extraction Using NLP
Speech to Text and Topic Extraction Using NLP
Speech-to-text frameworks and toolkits
Google Speech Commands Dataset
Neural network architecture
Training the model
Summary
Questions
Further reading
6
Predicting Stock Prices using Gaussian Process Regression
Predicting Stock Prices using Gaussian Process Regression
Understanding Bayes' rule
 Introducing Bayesian inference
Introducing Gaussian processes
Applying GPs to stock market prediction
Creating a stock price prediction model
Understanding the results obtained
Summary
Questions
7
Credit Card Fraud Detection using Autoencoders
Credit Card Fraud Detection using Autoencoders
Understanding auto-encoders
Building a fraud detection model
Summary
Questions
8
Generating Uncertainty in Traffic Signs Classifier Using Bayesian Neural Networks
Generating Uncertainty in Traffic Signs Classifier Using Bayesian Neural Networks
Understanding Bayesian deep learning
Understanding TensorFlow probability, variational inference, and Monte Carlo methods
Building a Bayesian neural network
Summary
Questions
9
Generating Matching Shoe Bags from Shoe Images Using DiscoGANs
Generating Matching Shoe Bags from Shoe Images Using DiscoGANs
Understanding generative models
Understanding DiscoGANs
Building a DiscoGAN model
Summary
Questions
10
Classifying Clothing Images using Capsule Networks
Classifying Clothing Images using Capsule Networks
Understanding the importance of capsule networks
Understanding capsules
The dynamic routing algorithm
CapsNet for classifying Fashion MNIST images
Training and testing the model
Reconstructing sample images
Limitations of capsule networks
Summary
11
Making Quality Product Recommendations Using TensorFlow
Making Quality Product Recommendations Using TensorFlow
Recommendation systems
Content-based filtering
Collaborative filtering
Hybrid systems
Matrix factorization
Introducing the Retailrocket dataset
Exploring the Retailrocket dataset
Pre-processing the data
The matrix factorization model for Retailrocket recommendations
The neural network model for Retailrocket recommendations
Summary
Questions
Further reading
12
Object Detection at a Large Scale with TensorFlow
Object Detection at a Large Scale with TensorFlow
Introducing Apache Spark
Understanding distributed TensorFlow
Learning about TensorFlowOnSpark
Object detection using TensorFlowOnSpark and Sparkdl
Summary
13
Generating Book Scripts Using LSTMs
Generating Book Scripts Using LSTMs
Understanding recurrent neural networks
Pre-processing the data
Defining the model
Training the model
Defining and training a text-generating model
Generating book scripts
Summary
Questions
14
Playing Pacman Using Deep Reinforcement Learning
Playing Pacman Using Deep Reinforcement Learning
Reinforcement learning
Reinforcement learning versus supervised and unsupervised learning
Components of Reinforcement Learning
OpenAI Gym 
Creating a Pacman game in OpenAI Gym 
DQN for deep reinforcement learning
Applying DQN to a game
Summary
Further Reading
15
What is Next?
What is Next?
Implementing TensorFlow in production
Recommendations for building AI applications
Limitations of deep learning
AI applications in industries
Ethical considerations in AI
Summary
Other Books You May Enjoy
Other Books You May Enjoy
Leave a review - let other readers know what you think
Index
Index

Reinforcement learning

Reinforcement learning is a type of machine learning in which an agent learns from the environment. The agent takes actions and, as a result of the actions, the environment returns observations and rewards. From the observation and rewards, the agent learns the policy and takes further actions, thus continuing the sequence of actions, observations, and rewards. In the long run, the agent has to learn the policy such that, when it takes actions based on the policy, it does so in such a way as to maximize the long-term rewards. 

Previous Section
End of Section 2
Next Section