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.
Table of Contents (23 chapters)
Title Page
Copyright and Credits
Dedication
About Packt
Contributors
Preface
Index

Understanding Bayesian deep learning


We've all understood the basics of Bayes' rule, as explained in Chapter 6, Predicting Stock Prices using Gaussian Process Regression.

For Bayesian machine learning, we use the same formula as Bayes' rule to learn model parameters (

) from the given data, 

. The formula, then, looks like this:

Here, 

or the probability of observed data is also called evidence. This is always difficult to compute. One brute-force way is to integrate out

 for all the values of model parameters, but this is obviously too expensive to evaluate.

 is the prior on parameters, which is nothing but some randomly initialized value of parameters in most cases. Generally, we don't care about setting the priors perfectly as we expect the inference procedure to converge to the right value of parameters.

is known as the likelihood of data, given the modeling parameters. Effectively, it shows how likely it is to obtain the given observations in the data when given the model parameters. We...