Book Image

Artificial Intelligence and Machine Learning Fundamentals

By : Zsolt Nagy
Book Image

Artificial Intelligence and Machine Learning Fundamentals

By: Zsolt Nagy

Overview of this book

Machine learning and neural networks are pillars on which you can build intelligent applications. Artificial Intelligence and Machine Learning Fundamentals begins by introducing you to Python and discussing AI search algorithms. You will cover in-depth mathematical topics, such as regression and classification, illustrated by Python examples. As you make your way through the book, you will progress to advanced AI techniques and concepts, and work on real-life datasets to form decision trees and clusters. You will be introduced to neural networks, a powerful tool based on Moore's law. By the end of this book, you will be confident when it comes to building your own AI applications with your newly acquired skills!

Related Content you might be interested in

Current Title:

Small book image
Artificial Intelligence and Machine Learning Fundamentals
Zsolt Nagy
Dec, 2018 | 330 pages
Small book image
Artificial Intelligence with Python
Prateek Joshi
Jan, 2017 | 446 pages
Small book image
Machine Learning with scikit-learn Quick Start Guide
Kevin Jolly
Oct, 2018 | 172 pages
Small book image
Artificial Intelligence with Python
Alberto Artasanchez | Prateek Joshi
Jan, 2020 | 618 pages
Table of Contents (10 chapters)
Artificial Intelligence and Machine Learning Fundamentals
Artificial Intelligence and Machine Learning Fundamentals
Preface
Preface
Free Chapter
1
Principles of Artificial Intelligence
Principles of Artificial Intelligence
Introduction
Fields and Applications of Artificial Intelligence
AI Tools and Learning Models
The Role of Python in Artificial Intelligence
Python for Game AI
Summary
2
AI with Search Techniques and Games
AI with Search Techniques and Games
Introduction
Heuristics
Pathfinding with the A* Algorithm
Game AI with the Minmax Algorithm and Alpha-Beta Pruning
Summary
3
Regression
Regression
Introduction
Linear Regression with One Variable
Linear Regression with Multiple Variables
Polynomial and Support Vector Regression
Summary
4
Classification
Classification
Introduction
The Fundamentals of Classification
Classification with Support Vector Machines
Summary
5
Using Trees for Predictive Analysis
Using Trees for Predictive Analysis
Introduction to Decision Trees
Random Forest Classifier
Summary
6
Clustering
Clustering
Introduction to Clustering
The k-means Algorithm
Mean Shift Algorithm
Summary
7
Deep Learning with Neural Networks
Deep Learning with Neural Networks
Introduction
TensorFlow for Python
Introduction to Neural Networks
Deep Learning
Summary
8
Appendix A
Appendix A
Lesson 1: Principles of AI
Lesson 2: AI with Search Techniques and Games
Lesson 4: Classification
Lesson 5: Using Trees for Predictive Analysis
Lesson 6: Clustering
Lesson 7: Deep Learning with Neural Networks

Heuristics

In this topic, we will formalize informed search techniques by defining and applying heuristics to guide our search.

Uninformed and Informed Search

In the Tic-Tac-Toe example, we implemented a greedy algorithm that first focused on winning, and then focused on not losing. When it comes to winning the game immediately, the greedy algorithm is optimal, because there is never a better step than winning the game. When it comes to not losing, it matters how we avoid the loss. Our algorithm simply chose a random safe move without considering how many winning opportunities we have created.

Breadth First Search and Depth First Search are uninform, because they consider all possible states in the game. An informed search explores the space of available states intelligently.

Creating Heuristics

If we want to make better decisions, we apply heuristics to guide the search in the right direction by considering longer-term utility. This way, we can make a more informed decision in the present...

Previous Section
End of Section 3
Next Section