Book Image

Go Machine Learning Projects

By : Xuanyi Chew
Book Image

Go Machine Learning Projects

By: Xuanyi Chew

Overview of this book

Go is the perfect language for machine learning; it helps to clearly describe complex algorithms, and also helps developers to understand how to run efficient optimized code. This book will teach you how to implement machine learning in Go to make programs that are easy to deploy and code that is not only easy to understand and debug, but also to have its performance measured. The book begins by guiding you through setting up your machine learning environment with Go libraries and capabilities. You will then plunge into regression analysis of a real-life house pricing dataset and build a classification model in Go to classify emails as spam or ham. Using Gonum, Gorgonia, and STL, you will explore time series analysis along with decomposition and clean up your personal Twitter timeline by clustering tweets. In addition to this, you will learn how to recognize handwriting using neural networks and convolutional neural networks. Lastly, you'll learn how to choose the most appropriate machine learning algorithms to use for your projects with the help of a facial detection project. By the end of this book, you will have developed a solid machine learning mindset, a strong hold on the powerful Go toolkit, and a sound understanding of the practical implementations of machine learning algorithms in real-world projects.
Table of Contents (12 chapters)

Pigo

Pigo is a Go library for detecting faces by using the PICO algorithm. Compared to the Viola-Jones method, PICO is fast. Naturally, PIGO is fast too. Add this to the fact that GoCV uses cgo, which adds a penalty for speed, and PIGO may seem to be a better option overall. However, it must be noted that the PICO algorithm is more prone to false positives than the original Viola-Jones method.

Using the PIGO library is simple. The provided documentation is clear. However, PIGO was designed to run within the author's workflow. Differing from that workflow will require some tiny amount of extra work. Specifically, the author draws images using external helpers such as github.com/fogleman/gg. We shan't. However, the work isn't much.

To install pigo, simply run go get -u github.com/esimov/pigo/....