Book Overview & Buying
Table Of Contents

Hands-On Artificial Intelligence for Beginners

By : Dindi, Patrick D. Smith

Buy this Book

Hands-On Artificial Intelligence for Beginners

By: Dindi, Patrick D. Smith

Buy this Book

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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

The History of AI

The beginnings of AI –1950–1974

Rebirth –1980–1987

The modern era takes hold – 1997-2005

Deep learning and the future – 2012-Present

Summary

Machine Learning Basics

Technical requirements

Applied math basics

Basic statistics and probability theory

Constructing basic machine learning algorithms

Basic tuning

Summary

Platforms and Other Essentials

Technical requirements

TensorFlow, PyTorch, and Keras

Cloud computing essentials

CPUs, GPUs, and other compute frameworks

Summary

Your First Artificial Neural Networks

Technical requirements

Network building blocks

The training process

Summary

Convolutional Neural Networks

Overview of CNNs

Convolutional layers

Pooling layers

Fully connected layers

The training process

CNNs for image tagging

Summary

Recurrent Neural Networks

Technical requirements

The building blocks of RNNs

Memory units – LSTMs and GRUs

Sequence processing with RNNs

Extensions of RNNs

Summary

Generative Models

Technical requirements

Getting to AI – generative models

Variational autoencoders

Generative adversarial networks

Other forms of generative models

Summary

References

Reinforcement Learning

Technical requirements

Principles of reinforcement learning

Q–learning

Policy optimization

Summary

Deep Learning for Intelligent Agents

Technical requirements

Word embeddings

Word2vec

GloVe

Constructing a basic agent

Summary

Deep Learning for Game Playing

Technical requirements

Introduction

Networks for board games

Networks for video games

Summary

Deep Learning for Finance

Requirements

Introduction to AI in finance

Deep learning in trading

Deep learning in asset management

Summary

Deep Learning for Robotics

Technical requirements

Introduction

Setting up your environment

Setting up a deep deterministic policy gradients model

Summary

References

Deploying and Maintaining AI Applications

Technical requirements

Introduction

Deploying your applications

Scaling your applications

Testing and maintaining your applications

Summary

References

Other Books You May Enjoy

Leave a review - let other readers know what you think

Constructing basic machine learning algorithms

As mentioned in the last chapter, machine learning is a term that was developed as a reaction to the first AI winter. Today, we generally consider machine learning to be the overarching subject area for deep learning and ANNs in general.

Most machine learning solutions can be broken down into either a classification problem or a regression problem. A classification problem is when the output variables are categorical, such as fraud or not fraud. A regression problem is when the output is continuous, such as dollars or site visits. Problems with numerical output can be categorical, but are typically transformed to have a categorical output such as first class and second class.

Within machine learning, we have supervised algorithms and unsupervised algorithms. In this section, we will introduce these types of algorithms and explore...