Book Image

Python Deep Learning

By : Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants
Book Image

Python Deep Learning

By: Valentino Zocca, Gianmario Spacagna, Daniel Slater, Peter Roelants

Overview of this book

With an increasing interest in AI around the world, deep learning has attracted a great deal of public attention. Every day, deep learning algorithms are used broadly across different industries. The book will give you all the practical information available on the subject, including the best practices, using real-world use cases. You will learn to recognize and extract information to increase predictive accuracy and optimize results. Starting with a quick recap of important machine learning concepts, the book will delve straight into deep learning principles using Sci-kit learn. Moving ahead, you will learn to use the latest open source libraries such as Theano, Keras, Google's TensorFlow, and H20. Use this guide to uncover the difficulties of pattern recognition, scaling data with greater accuracy and discussing deep learning algorithms and techniques. Whether you want to dive deeper into Deep Learning, or want to investigate how to get more out of this powerful technology, you’ll find everything inside.
Table of Contents (18 chapters)
Python Deep Learning
Credits
About the Authors
About the Reviewer
www.PacktPub.com
Customer Feedback
Preface
Index

Using the min-max algorithm to value game states


Say we want to work out the best move in a zero sum, deterministic, perfect information game. How can we do this? Well, first off, given that we have perfect information, we know exactly what moves are available to us. Given that the game is deterministic, we know exactly what state the game will change to due to each of those moves. The same is then true for the opponent's move as well; we know exactly what possible moves they have and how the state would look as a result of each of those moves.

One approach for finding the best move would be to construct a full tree of every possible move for each player at each state until we reach a state where the game is over. This end state of the game is also known as the terminal state. We can assign a value to this terminal state; a win could carry the value 1, a draw 0, and a loss -1. These values reflect the states' desirability to us. We would prefer a win than a draw and a draw to a loss. Figure...