How to Use Machine Learning in Chemistry by Cartwright, Hugh M;

Short description:

Covering the underlying principles of machine learning as well as practical applications in science this book is an ideal primer for newcomers to the field.

Long description:

Machine learning and artificial intelligence are hot topics across the sciences but what are they? How do machines learn and how can we apply them to problems in the chemical sciences?

Written as a primer for anyone new to the area of machine learning, this book provides an overview of the principles that underly its use in science and discusses its use as a practical tool in research. Readers will develop an understanding of key terminology and learn about the critical factors to be taken into account when using machine learning in science.

Drawing on examples from chemistry, this book covers topics including the mechanics of networks and training, representations in chemistry and solving issues with data. With a focus on practical implementation and how to ensure that your applications are robust, this is a fantastic starting point for anyone looking to incorporate machine learning into their work.

Table of Contents:

• Introduction
• Learning and Training
• Structure of a Machine Learning Model
• How Do We Know When Training Should End?
• The (Several) Roles of Random Numbers
• Hyperparameters: How to Make a Good Model Better
• How to Bungle Training in a Few Easy Steps
• Further Ways to Improve the Model and Data
• Representation, Descriptors and Properties
• Bayesian Optimisation
• Can We Understand How Machine Learning Models Reason?
• Other Types of Network
• A Glance Ahead