Название: Practical Python Artificial Intelligence Programming
Автор: Mark Watson
Издательство: Leanpub
Год: 2023-02-02
Страниц: 129
Язык: английский
Формат: pdf (true), epub
Размер: 10.2 MB

A fun dive into AI programming with Python.

We will cover Deep Learning, old fashioned symbolic AI, broad coverage of data sources as well as wide range of tips and techniques for using Python both in experiments and in production.

This book is intended, dear reader, to show you a wide variety of practical Artificial Intelligence (AI) techniques and examples, and to be a jumping off point when you discover things that interest you or may be useful in your work. A common theme here is covering AI programming tasks that used to be difficult or impossible but are now much simpler using deep learning, of at least possible. I also cover a wide variety on non-deep learning material including a chapter on Symbolic AI that has historic interest and some current practical value.

Why Python? Python is a very high level language that is easily readable by other programmers. Since Python is one of the most popular programming languages there are many available libraries and frameworks. The best code is code that we don’t have to write ourselves as long as third party code is open source so we can read and modify it if needed. Another reason to use Python, that we lean heavily on in this book, is using pre-trained deep learning models that are wrapped into Python packages and libraries.

“Classic” Machine Learning (ML) is a broad field that encompasses a variety of algorithms and techniques for learning from data. These techniques are used to make predictions, classify data, and uncover patterns and insights. Some of the most common types of classic ML algorithms include:

• Linear regression: a method for modeling the relationship between a dependent variable and one or more independent variables by fitting a linear equation to the observed data.
• Logistic regression: a method for modeling the relationship between a binary dependent variable and one or more independent variables by fitting a logistic function to the observed data.
• Decision Trees: a method for modeling decision rules based on the values of the input variables, which are organized in a tree-like structure.
• Random Forest: a method that creates multiple decision trees and averages the results to improve the overall performance of the model
• K-Nearest Neighbors (K-NN): a method for classifying data by finding the K-nearest examples in the training data and assigning the most similar common class among them.
• Naive Bayes: a method for classifying data based on Bayes’ theorem and the assumption of independence between the input variables.

We will be covering a very small subset of “classic” ML, and then dive deeper into Deep Learning in later chapters. Here we cover just a single example of what I think of as “classic machine learning” using the scikit-learn Python library. Later we cover deep learning in three separate chapters. Deep learning models are more general and powerful but it is important to recognize the types of problems that can be solved using the simpler techniques.

The author has been a general AI practitioner since 1982, developed neural network products and projects since 1986, and deep learning since 2015. He has written 20+ books and has 50+ US Patents.

Contents:
Preface
Part I - Getting Started
Python Development Environment
“Classic” Machine Learning
Symbolic AI
Part II - Knowledge Representation
Getting Setup To Use Graph and Relational Databases
Semantic Web, Linked Data and Knowledge Graphs
Part III - Deep Learning
The Basics of Deep Learning
Natural Language Processing Using Deep Learning
Part IV - Overviews of Image Generation, Reinforcement Learning, and Recommendation Systems
Overview of Image Generation
Overview of Reinforcement Learning (Optional Material)
Overview of Recommendation Systems
Book Wrap-up