Book Image

Building Machine Learning Projects with TensorFlow

By : Rodolfo Bonnin
Book Image

Building Machine Learning Projects with TensorFlow

By: Rodolfo Bonnin

Overview of this book

<p>This book of projects highlights how TensorFlow can be used in different scenarios - this includes projects for training models, machine learning, deep learning, and working with various neural networks. Each project provides exciting and insightful exercises that will teach you how to use TensorFlow and show you how layers of data can be explored by working with Tensors. Simply pick a project that is in line with your environment and get stacks of information on how to implement TensorFlow in production.</p>

Related Content you might be interested in

Current Title:

Small book image
Building Machine Learning Projects with TensorFlow
Rodolfo Bonnin
Nov, 2016 | 282 pages
No titles found
Table of Contents (16 chapters)
Building Machine Learning Projects with TensorFlow
Building Machine Learning Projects with TensorFlow
Credits
Credits
About the Author
About the Author
About the Reviewer
About the Reviewer
www.PacktPub.com
www.PacktPub.com
Preface
Preface
Free Chapter
1
Exploring and Transforming Data
Exploring and Transforming Data
TensorFlow's main data structure - tensors
Handling the computing workflow - TensorFlow's data flow graph
Running our programs - Sessions
Basic tensor methods
Summary
2
Clustering
Clustering
Learning from data - unsupervised learning
Clustering
k-means
k-nearest neighbors
Project 1 - k-means clustering on synthetic datasets
Project 2 - nearest neighbor on synthetic datasets
Summary
3
Linear Regression
Linear Regression
Univariate linear modelling function
Determination of the cost function
Minimizing the cost function
Example section
Example 1 - univariate linear regression
Example - multivariate linear regression
Summary
4
Logistic Regression
Logistic Regression
Problem description
Logistic function predecessor - the logit functions
The logistic function
Example 1 - univariate logistic regression
Example 2 - Univariate logistic regression with skflow
Summary
5
Simple FeedForward Neural Networks
Simple FeedForward Neural Networks
Preliminary concepts
First project - Non linear synthetic function regression
Second project - Modeling cars fuel efficiency with non linear regression
Third project - Learning to classify wines: Multiclass classification
Summary
6
Convolutional Neural Networks
Convolutional Neural Networks
Origin of convolutional neural networks
Example 1 - MNIST digit classification
Example 2 - image classification with the CIFAR10 dataset
Summary
7
Recurrent Neural Networks and LSTM
Recurrent Neural Networks and LSTM
Recurrent neural networks
Example 1 - univariate time series prediction with energy consumption data
Example 2 - writing music "a la" Bach
Summary
8
Deep Neural Networks
Deep Neural Networks
Deep neural network definition
Deep network architectures through time
Alexnet
Inception v3
Residual Networks (ResNet)
Example - painting with style - VGG style transfer
Summary
9
Running Models at Scale – GPU and Serving
Running Models at Scale – GPU and Serving
GPU support on TensorFlow
Example 1 - assigning an operation to the GPU
Example 2 - calculating Pi number in parallel
Distributed TensorFlow
Example 3 - distributed Pi calculation
Example 4 - running a distributed model in a cluster
Summary
10
Library Installation and Additional Tips
Library Installation and Additional Tips
Linux installation
Windows installation
MacOS X installation
Summary

Summary

In this chapter, we have reviewed some of the main ways in which a TensorFlow installation can be performed.

Even if the list of possibilities is finite, every month or so we see a new architecture or processor being supported, so we can only expect more and more application fields for this technology.

Previous Section
End of Chapter 10
Next Chapter