New edition of the bestselling guide to artificial intelligence with Python, updated to Python 3.x, with seven new chapters that cover RNNs, AI and Big Data, fundamental use cases, chatbots, and more.
▶Book Description
Artificial Intelligence with Python, Second Edition is an updated and expanded version of the bestselling guide to artificial intelligence using the latest version of Python 3.x. Not only does it provide you an introduction to artificial intelligence, this new edition goes further by giving you the tools you need to explore the amazing world of intelligent apps and create your own applications.
This edition also includes seven new chapters on more advanced concepts of Artificial Intelligence, including fundamental use cases of AI; machine learning data pipelines; feature selection and feature engineering; AI on the cloud; the basics of chatbots; RNNs and DL models; and AI and Big Data.
Finally, this new edition explores various real-world scenarios and teaches you how to apply relevant AI algorithms to a wide swath of problems, starting with the most basic AI concepts and progressively building from there to solve more difficult challenges so that by the end, you will have gained a solid understanding of, and when best to use, these many artificial intelligence techniques.
▶What You Will Learn
-Understand what artificial intelligence, machine learning, and data science are
-Explore the most common artificial intelligence use cases
-Learn how to build a machine learning pipeline
-Assimilate the basics of feature selection and feature engineering
-Identify the differences between supervised and unsupervised learning
-Discover the most recent advances and tools offered for AI development in the cloud
-Develop automatic speech recognition systems and chatbots
-Apply AI algorithms to time series data
▶Key Features
-Completely updated and revised to Python 3.x
-New chapters for AI on the cloud, recurrent neural networks, deep learning models, and feature selection and engineering
-Learn more about deep learning algorithms, machine learning data pipelines, and chatbots
▶Who This Book Is For
The intended audience for this book is Python developers who want to build real-world Artificial Intelligence applications. Basic Python programming experience and awareness of machine learning concepts and techniques is mandatory.
▶What this book covers
- Chapter 1, Introduction to Artificial Intelligence
This chapter provides some basic definitions and groupings that will be used throughout the book. It will also provide an overall classification of the artificial intelligence and machine learning fields as they exist today.
- Chapter 2, Fundamental Use Cases for Artificial Intelligence
Artificial Intelligence is a fascinating topic and a vast field of knowledge. In its current state it generates more questions than it answers, but there are certainly many places where artificial intelligence is being applied, in many instances without us even realizing. Before we delve into the fundamental algorithms that drive AI, we will analyze some of the most popular use cases for the technology as of today.
- Chapter 3, Machine Learning Pipelines
Model training is only a small piece of the machine learning process. Data scientists often spend a significant amount of time cleansing, transforming, and preparing data to get it ready to be consumed by an AI model. Since data preparation is such a time-consuming activity, we will present state-of-the-art techniques to facilitate this activity as well as other components that a well-designed production data pipeline should possess.
- Chapter 4, Feature Selection and Feature Engineering
Model performance can be improved by selecting the right dimensions to pass to the model as well as discovering new dimensions that can enrich the input datasets. This chapter will demonstrate how new features can be created from existing ones as well as from external sources. It will also cover how to eliminate redundant or lowvalue features.
- Chapter 5, Classification and Regression Using Supervised Learning
This chapter defines in detail supervised learning. It provides a taxonomy of the various methods and algorithms for problems that fall under this classification.
- Chapter 6, Predictive Analytics with Ensemble Learning
Ensemble learning is a powerful technique that allows you to aggregate the power of individual models. This chapter goes over the different ensemble methods as well as guidance on when to use each of them. Finally, the chapter will cover how to apply these techniques to real-world event prediction.
- Chapter 7, Detecting Patterns with Unsupervised Learning
This chapter will explore the concepts of clustering and data segmentation and how they are related to unsupervised learning. It will also cover how to perform clustering and how to apply various clustering algorithms. It will show several examples that allow the reader to visualize how these algorithms work. Lastly, it will cover the application of these algorithms to perform clustering and segmentation in real-world situations.
- Chapter 8, Building Recommender Systems
This chapter will demonstrate how to build recommender systems. It will also show how to persist user preferences. It will cover the concepts of nearest neighbor search and collaborative filtering. Finally, there will be an example showing how to build a movie recommendation system.
- Chapter 9, Logic Programming
This chapter will cover how to write programs using logic programming. It will discuss various programming paradigms and see how programs are constructed with logic programming. It will highlight the building blocks of logic programming and see how to solve problems in this domain. Finally, various Python program implementations will be built for various solvers that tackle a variety of problems.
- Chapter 10, Heuristic Search Techniques
This chapter covers heuristic search techniques. Heuristic search techniques are used to search through the solution space to come up with answers. The search is conducted using heuristics that guide the search algorithm. Heuristics allow the algorithm to speed up the process, which would otherwise take a long time to arrive at the solution.
- Chapter 11, Genetic Algorithms and Genetic Programming
We will discuss the basics of genetic programming and its importance in the field of AI. We will learn how to solve simple problems using genetic algorithms. We will understand some underlying concepts that are used to do genetic programming. We will then see how to apply this to a real-world problem.
- Chapter 12, Artificial Intelligence on the Cloud
The cloud enables us to accelerate AI development, workloads, and deployment. In this chapter, we will explore the different offerings from the most popular vendors that enable and accelerate AI projects.
- Chapter 13, Building Games with Artificial Intelligence
This chapter will cover how to build games using artificial intelligence techniques. Search algorithms will be used to develop winning game strategies and tactics. Finally, intelligent bots will be built for a variety of games.
- Chapter 14, Building a Speech Recognizer
This chapter will cover how to perform speech recognition. It will show how to process speech data and extract features from it. Finally, it will demonstrate how to use the extracted features to build a speech recognition system.
- Chapter 15, Natural Language Processing
This chapter will focus on the important area of AI known as Natural Language Processing (NLP). It will discuss various concepts such as tokenization, stemming, and lemmatization to process text. It will also cover how to build a Bag of Words model and use it to classify text. It will demonstrate how machine learning can be used to analyze the sentiment of a given sentence. Lastly, it will show topic modeling and go over the implementation of a system to identify topics in a document.
- Chapter 16, Chatbots
Chatbots can help to save money and better serve customers by increasing productivity and deflecting calls. In this chapter, we will cover the basics of chatbots and the tools available to build them. Finally, we will build a full-blown chatbot from scratch that will implement a real-world use case including error handling, connecting it to an external API, and deploying the chatbot.
- Chapter 17, Sequential Data and Time Series Analysis
We will discuss the concept of probabilistic reasoning. We will learn how to apply that concept to build models for sequential data. We will learn about the various characteristics of time-series data. We will discuss Hidden Markov Models and how to use them to analyze sequential data. We will then use this technique to analyze stock market data.
- Chapter 18, Image Recognition
We will discuss how to work with images in this chapter. We will learn how to detect and track objects in a live video. We will then learn how to apply those techniques to track parts of the human face.
- Chapter 19, Neural Networks
We will discuss artificial neural networks. We will learn about perceptrons and see how they are used to build neural networks. We will learn how to build singlelayered and multi-layered neural networks. We will discuss how a neural network learns about the training data and builds a model. We will learn about the cost function and backpropagation. We will then use these techniques to perform optical character recognition.
- Chapter 20, Deep Learning with Convolutional Neural Networks
We will discuss the basics of deep learning in this chapter. The reader will be introduced to various concepts in convolutional neural networks and how they can be used for image recognition. We will discuss various layers in a convolutional neural network. We will then use these techniques to build a real-world application.
- Chapter 21, Recurrent Neural Networks and Other Deep Learning Models
This chapter will continue to cover other types of deep learning algorithms. It will start with coverage of recurrent neural networks and it will then cover newer algorithms such as the Attention, Self-Attention, and Transformer models. This chapter will cover the use cases where these networks are used and the advantages of using these kinds of model architecture, as well as their limitations. Finally, the techniques discussed will be used to build a real-world application.
- Chapter 22, Creating Intelligent Agents with Reinforcement Learning
This chapter will define reinforcement learning (RL) as well as cover the components within an RL model. It will detail the techniques used to build RL systems. Finally, it will demonstrate how to build learning agents that can learn by interacting with the environment.
- Chapter 23, Artificial Intelligence and Big Data
This chapter will analyze how big data techniques can be applied to accelerate machine learning pipelines as well as covering different techniques that can be used to streamline dataset ingestion, transformation, and validation. Finally, it will walk the reader through an actual example using Apache Spark to demonstrate the concepts covered in the chapter.
