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)

Network building blocks

The most basic form of an ANN is known as a feedforward network, sometimes called a multi-layer perceptron. These models, while simplistic in nature, contain the core building blocks for the various types of ANN that we will examine going forward.

In essence, a feedforward neural network is nothing more than a directed graph; there are no loops of recurrent connections between the layers, and information simply flows forward through the graph. Traditionally, when these networks are illustrated, you'll see them represented as in the following diagram:

A feedforward neural network

In this most basic form, ANNs are typically organized into three basic layers; an input layer, a hidden layer, and an output layer, each made up of many basic input/output processing units commonly referred to as neurons. While it's helpful to view networks as basic...