Hands-On Artificial Intelligence for Beginners

An introduction to AI concepts, algorithms, and their implementation

Patrick D. Smith 지음

Packt(GCO Science) 2018년 10월 31일 출간

작품소개

책소개

▶Book Description
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.

▶What You Will Learn
？ Use TensorFlow packages to create AI systems
？ Build feedforward, convolutional, and recurrent neural networks
？ Implement generative models for text generation
？ Build reinforcement learning algorithms to play games
？ Assemble RNNs, CNNs, and decoders to create an intelligent assistant
？ Utilize RNNs to predict stock market behavior
？ Create and scale training pipelines and deployment architectures for AI systems

▶Key Features
？ Enter the world of AI with the help of solid concepts and real-world use cases
？ Explore AI components to build real-world automated intelligence
？ Become well versed with machine learning and deep learning concepts

▶Who This Book Is For
This book is designed for beginners in AI, aspiring AI developers, as well as machine learning enthusiasts with an interest in leveraging various algorithms to build powerful AI applications.

목차

▶TABLE of CONTENTS
1: THE HISTORY OF AI
2: MACHINE LEARNING BASICS
3: PLATFORMS AND OTHER ESSENTIALS
4: YOUR FIRST ARTIFICIAL NEURAL NETWORKS
5: CONVOLUTIONAL NEURAL NETWORKS
6: RECURRENT NEURAL NETWORKS
7: GENERATIVE MODELS
8: REINFORCEMENT LEARNING
9: DEEP LEARNING FOR INTELLIGENT AGENTS
10: DEEP LEARNING FOR GAME PLAYING
11: DEEP LEARNING FOR FINANCE
12: DEEP LEARNING FOR ROBOTICS
13: DEPLOYING AND MAINTAINING AI APPLICATIONS

책 속으로

▶What this book covers
？ Chapter 1, The History of AI, begins by discussing the mathematical basis of AI and how certain theorems evolved. Then, we'll look at the research done in the 1980s and 90s to improve ANNs, we'll look at the AI winter, and we'll finish off with how we arrived at where we are today.

？ Chapter 2, Machine Learning Basics, introduces the fundamentals of machine learning and AI. Here, we will cover essential probability theory, linear algebra, and other elements that will lay the groundwork for the future chapters.

？ Chapter 3, Platforms and Other Essentials, introduces the deep learning libraries of Keras and TensorFlow and moves onto an introduction of basic AWS terminology and concepts that are useful for deploying your networks in production. We'll also introduce CPUs and GPUs, as well as other forms of compute architecture that you should be familiar with when building deep learning solutions.

？ Chapter 4, Your First Artificial Neural Networks, explains how to build our first artificial neural network. Then, we will learn ability of the core elements of ANNs and construct a simple single layer network both in Keras and TensorFlow so that you understand how the two languages work. With this simple network, we will do a basic classification task, such as the MNIST OCR task.

？ Chapter 5, Convolutional Neural Networks, introduces the convolutional neural network and explains its inner workings. We'll touch upon the basic building blocks of convolutions, pooling layers, and other elements. Lastly, we'll construct a Convolutional Neural Network for image tagging.

？ Chapter 6, Recurrent Neural Networks, introduces one of the workhorses of deep learning and AI―the recurrent neural network. We'll first introduce the conceptual underpinnings of recurrent neural networks, with a specific focus on utilizing them for natural language processing tasks. We'll show how one can generate text utilizing you of these networks and see how they can be utilized for predictive financial models.

？ Chapter 7, Generative Models, covers generative models primarily through the lens of GANs, and we'll look at how we can accomplish each of the above tasks with GANs.

？ Chapter 8, Reinforcement Learning, introduces additional forms of neural networks. First, we'll take a look at autoencoders, which are unsupervised learning algorithms that help us recreate inputs when we don't have access to input data. Afterwards, we'll touch upon other forms of networks, such as the emerging geodesic neural networks.

？ Chapter 9, Deep Learning for Intelligent Assistant, focuses on utilizing our knowledge of various forms of neural networks from the previous section to make an intelligent assistant, along the lines of Amazon's Alexa or Apple's Siri. We'll learn about and utilize word embeddings, recurrent neural networks, and decoders.

？ Chapter 10, Deep Learning for Game Playing, explains how to construct game-playing algorithms with reinforcement learning. We'll look at several different forms of games, from simple Atari-style games to more advanced board games. We'll touch upon the methods that Google Brain utilized to build AlphaGo.

？ Chapter 11, Deep Learning for Finance, shows how to create an advanced market prediction system in TensorFlow utilizing RNNs.

？ Chapter 12, Deep Learning for Robotics, uses deep learning to teach a robot to move objects. We will first train the neural network in simulated environments and then move on to real mechanical parts with images acquired from a camera.

？ Chapter 13, Scale, Deploy and Maintain AI Application, introduces methods for creating and scaling training pipelines and deployment architectures for AI systems.

출판사 서평

▶ Preface
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. AI 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 AI is and how to design and build intelligent applications. This book will teach you to harness packages such as TensorFlow to create powerful AI systems. You will begin by 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, directing self-driving cars, 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.

작가정보

저자(글) Patrick D. Smith

Patrick D. Smith is the Data Science Lead for Excella in Arlington, Virginia, where he founded the data science and machine learning team. Prior to Excella, Patrick was the lead instructor for the data science program at General Assembly in Washington, DC, as well as a data scientist with Booz Allen Hamilton's Strategic Innovations Group. He holds a bachelor's degree from The George Washington University in International Economics, and is currently a part-time masters student in software engineering at Harvard University.