Artificial Intelligence and Machine Learning Fundamentals

Develop real-world applications powered by the latest AI advances

Zsolt Nagy

• Publisher: Packt Publishing
• Year: 2018
• Print ISBN: 9781789801651
• eBook ISBN: 9781789809206
• Edition: 1
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Create AI applications in Python and lay the foundations for your career in data science

Key Features

• Practical examples that explain key machine learning algorithms
• Explore neural networks in detail with interesting examples
• Master core AI concepts with engaging activities

Book Description

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!

What you will learn

• Understand the importance, principles, and fields of AI
• Implement basic artificial intelligence concepts with Python
• Apply regression and classification concepts to real-world problems
• Perform predictive analysis using decision trees and random forests
• Carry out clustering using the k-means and mean shift algorithms
• Understand the fundamentals of deep learning via practical examples

Who this book is for

Artificial Intelligence and Machine Learning Fundamentals is for software developers and data scientists who want to enrich their projects with machine learning. You do not need any prior experience in AI. However, it's recommended that you have knowledge of high school-level mathematics and at least one programming language (preferably Python).

>

Appendix

About

This section is included to assist the students to perform the activities in the book. It includes detailed steps that are to be performed by the students to achieve the objectives of the activities.

Chapter 1: Principles of AI

In the code, backslash (\) indicates a line break, where the code does not fit a line. A backslash at the end of the line escapes the newline character. This means that the content in the line following the backslash should be read as if it started where the backslash character is.

Activity 1: Generating All Possible Sequences of Steps in the tic-tac-toe Game

This section will explore the combinatoric explosion possible when two players play randomly. We will be using a program, building on the previous results that generate all possible sequences of moves between a computer player and a human player. Determine the number of different wins, losses, and draws in terms of action sequences. Assume that the human player may make any possible move. In this example, given that the computer player is playing randomly, we will examine the wins, losses, and draws belonging to two randomly playing players:

1. Create a function that maps the all_moves_from_board function on each element of a list of boards. This way, we will have all of the nodes of a decision tree in each depth:
   def all_moves_from_board(board, sign):
   move_list = []
   for i, v in enumerate(board):
   if v == EMPTY_SIGN:
   move_list.append(board[:i] + sign + board[i+1:])
   return move_list
2. The decision tree starts with [ EMPTY_SIGN * 9 ], and expands after each move:
   all_moves_from_board_list( [ EMPTY_SIGN * 9 ], AI_SIGN )
3. The output is as follows:
   ['X........',
   '.X.......',
   '..X......',
   '...X.....',
   '....X....',
   '.....X...',
   '......X..',
   '.......X.',
   '........X']
   ['XO.......',
   'X.O......',
   'X..O.....',
   'X...O....',
   'X....O...',
   'X.....O..',
   'X......O.',
   .
   .
   .
   .
   '......OX.',
   '.......XO',
   'O.......X',
   '.O......X',
   '..O.....X',
   '...O....X',
   '....O...X',
   '.....O..X',
   '......O.X',
   '.......OX']
4. Let's create a filter_wins function that takes the ended games out from the list of moves and appends them in an array containing the board states won by the AI player and the opponent player:
   def filter_wins(move_list, ai_wins, opponent_wins):
   for board in move_list:
   won_by = game_won_by(board)
   if won_by == AI_SIGN:
   ai_wins.append(board)
   move_list.remove(board)
   elif won_by == OPPONENT_SIGN:
   opponent_wins.append(board)
   move_list.remove(board)
5. In this function, the three lists can be considered as reference types. This means that the function does not return a value, instead but it manipulating these three lists without returning them.
6. Let's finish this section. Then with a count_possibilities function that prints the number of decision tree leaves that ended with a draw, won by the first player, and won by the second player:
   def count_possibilities():
   board = EMPTY_SIGN * 9
   move_list = [board]
   ai_wins = []
   opponent_wins = []
   for i in range(9):
   print('step ' + str(i) + '. Moves: ' + \ str(len(move_list)))
   sign = AI_SIGN if i % 2 == 0 else OPPONENT_SIGN
   move_list = all_moves_from_board_list(move_list, sign)
   filter_wins(move_list, ai_wins, opponent_wins)
   print('First player wins: ' + str(len(ai_wins)))
   print('Second player wins: ' + str(len(opponent_wins)))
   print('Draw', str(len(move_list)))
   print('Total', str(len(ai_wins) + len(opponent_wins) + \ len(move_list)))
7. We have up to 9 steps in each state. In the 0th, 2nd, 4th, 6th, and 8th iteration, the AI player moves. In all other iterations, the opponent moves. We create all possible moves in all steps and take out the ended games from the move list.
8. Then execute the number of possibilities to experience the combinatoric explosion.
   count_possibilities()
9. The output is as follows:
   step 0. Moves: 1
   step 1. Moves: 9
   step 2. Moves: 72
   step 3. Moves: 504
   step 4. Moves: 3024
   step 5. Moves: 13680
   step 6. Moves: 49...

Table of contents

• Preface
• Principles of Artificial Intelligence
• AI with Search Techniques and Games
• Regression
• Classification
• Using Trees for Predictive Analysis
• Clustering
• Deep Learning with Neural Networks
• Appendix