Book Image

Machine Learning Automation with TPOT

By : Dario Radečić
Book Image

Machine Learning Automation with TPOT

By: Dario Radečić

Overview of this book

The automation of machine learning tasks allows developers more time to focus on the usability and reactivity of the software powered by machine learning models. TPOT is a Python automated machine learning tool used for optimizing machine learning pipelines using genetic programming. Automating machine learning with TPOT enables individuals and companies to develop production-ready machine learning models cheaper and faster than with traditional methods. With this practical guide to AutoML, developers working with Python on machine learning tasks will be able to put their knowledge to work and become productive quickly. You'll adopt a hands-on approach to learning the implementation of AutoML and associated methodologies. Complete with step-by-step explanations of essential concepts, practical examples, and self-assessment questions, this book will show you how to build automated classification and regression models and compare their performance to custom-built models. As you advance, you'll also develop state-of-the-art models using only a couple of lines of code and see how those models outperform all of your previous models on the same datasets. By the end of this book, you'll have gained the confidence to implement AutoML techniques in your organization on a production level.
Table of Contents (14 chapters)
1
Section 1: Introducing Machine Learning and the Idea of Automation
3
Section 2: TPOT – Practical Classification and Regression
8
Section 3: Advanced Examples and Neural Networks in TPOT

Overview of deep learning

Deep learning is a subfield of machine learning that focuses on neural networks. Neural networks aren't that new as a concept – they were introduced back in the 1940s but didn't gain much in popularity until they started winning data science competitions (somewhere around 2010).

Potentially the biggest year for deep learning and AI was 2016, all due to a single event. AlphaGo, a computer program that plays the board game Go, defeated the highest-ranking player in the world. Before this event, Go was considered to be a game that computers couldn't master, as there are so many potential board configurations.

As mentioned before, deep learning is based on neural networks. You can think of neural networks as directed acyclic graphs – a graph consisting of vertices (nodes) and edges (connections). The input layer (the first layer, on the far left side) takes in the raw data from your datasets, passes it through one or multiple...