You're reading from Python Machine Learning Learn how to build powerful Python machine learning algorithms to generate useful data insights with this data analysis tutorial

Product type Paperback

Published in Sep 2015

Publisher Packt

ISBN-13 9781783555130

Length 454 pages

Edition 1st Edition

Languages

Python

Tools

SciPy

Concepts

Machine Learning

Author (1):

Sebastian Raschka

View More author details

Table of Contents (15) Chapters

Preface

1. Giving Computers the Ability to Learn from Data

2. Training Machine Learning Algorithms for Classification FREE CHAPTER

3. A Tour of Machine Learning Classifiers Using Scikit-learn

4. Building Good Training Sets – Data Preprocessing

5. Compressing Data via Dimensionality Reduction

6. Learning Best Practices for Model Evaluation and Hyperparameter Tuning

7. Combining Different Models for Ensemble Learning

8. Applying Machine Learning to Sentiment Analysis

9. Embedding a Machine Learning Model into a Web Application

10. Predicting Continuous Target Variables with Regression Analysis

11. Working with Unlabeled Data – Clustering Analysis

12. Training Artificial Neural Networks for Image Recognition

13. Parallelizing Neural Network Training with Theano

Index

Building, compiling, and running expressions with Theano

In this section, we will explore the powerful Theano tool, which has been designed to train machine learning models most effectively using Python. The Theano development started back in 2008 in the LISA lab (short for Laboratoire d'Informatique des Systèmes Adaptatifs (http://lisa.iro.umontreal.ca)) lead by Yoshua Bengio.

Before we discuss what Theano really is and what it can do for us to speed up our machine learning tasks, let's discuss some of the challenges when we are running expensive calculations on our hardware. Luckily, the performance of computer processors keeps on improving constantly over the years, which allows us to train more powerful and complex learning systems to improve the predictive performance of our machine learning models. Even the cheapest desktop computer hardware that is available nowadays comes with processing units that have multiple cores. In the previous chapters, we saw that many functions...