Book Image

Hands-On Artificial Intelligence for Beginners

By : Patrick D. Smith, David Dindi
Book Image

Hands-On Artificial Intelligence for Beginners

By: Patrick D. Smith, David Dindi

Overview of this book

Virtual Assistants, such as Alexa and Siri, process our requests, Google's cars have started to read addresses, and Amazon's prices and Netflix's recommended videos are decided by AI. Artificial Intelligence is one of the most exciting technologies and is becoming increasingly significant in the modern world. Hands-On Artificial Intelligence for Beginners will teach you what Artificial Intelligence is and how to design and build intelligent applications. This book will teach you to harness packages such as TensorFlow in order to create powerful AI systems. You will begin with reviewing the recent changes in AI and learning how artificial neural networks (ANNs) have enabled more intelligent AI. You'll explore feedforward, recurrent, convolutional, and generative neural networks (FFNNs, RNNs, CNNs, and GNNs), as well as reinforcement learning methods. In the concluding chapters, you'll learn how to implement these methods for a variety of tasks, such as generating text for chatbots, and playing board and video games. By the end of this book, you will be able to understand exactly what you need to consider when optimizing ANNs and how to deploy and maintain AI applications.
Table of Contents (15 chapters)

Principles of reinforcement learning

Reinforcement learning is based on the concept of learning from interaction with a surrounding environment and consequently rewarding positive actions taken in that environment. In reinforcement learning, we refer to our algorithm as the agent because it takes action on the world around it:

When an agent takes an action, it receives a reward or penalty depending on whether it took the correct action or not. Our goal in reinforcement learning is to let the agent learn to take actions that maximize the rewards it receives from its environment. These concepts are not at all new; in fact, they've been around for quite some time. What has allowed reinforcement learning to achieve such great heights has been the combination of new advances in deep learning, coupled with the computing power to handle increasingly complex scenarios.

There are...