my-workspace / AI-Programming-using-Python

This repository contains implementation of different AI algorithms, based on the 4th edition of amazing AI Book, Artificial Intelligence A Modern Approach

AI-Programming-using-Python

This repository contains implementation of different AI algorithms, based on the amazing AI book Artificial Intelligence: A Modern Approach (4th edition, 2020).

Contents

First part:

• Search problems
  • Uninformed search strategies:
    • BFS, DFS, UCS, DLS, IDS
  • Informed search strategies:
    • Gready, A-star

Example: solving 8-puzzle using search algorithms.

- Local search:
    - Hill climbing, Simulated Annealing, Genetic algorithms

Example solution found by simulated annealing for TSP problem (for 50 cities).

Example: solving 10-Queens using simulated annealing.

- Adversarial search and games
    - MiniMax, alpha-beta pruning

Python programming concepts

• Object oriented programming in Python
  • Using and defining special python methods (dunder methods).
  • Immutable objects.
  • Making an object hashable (implementing __hash__() and __eq__() methods.
  • Implementing decortors in Python.
  • Class methods and static methods.
  • __repr__() and __str__() methods.

Second part:

• Machine learning
  • Supervised learning:
    • KNN, Naive Bayes, Desision Trees, SVM, Neural Nets
  • Unsupervised learning:
    • k-Means clustering
  • Reinforcement learning
    • Q-learning

Example problems

• Search:
  • N-Puzzle, N-Queens, TSP
• Games:
  • Pacman, Chess
• Learning:
  • Pacman, Chess, etc.

Lesson 1: Uninformed (blind) search strategies

• Implementing data structures like stack, queue and priority queue
• Implementing N-Puzzle (8-Puzzle)
• Implementing uninformed search strategies: BFS, DFS, UCS, DLS, IDS
• Programming assignment

Lesson 2: Informed search strategies

• Implementing informed search strategies: Greedy, A-star
• Programming assignment

Lesson 3: Local search

• Implementing N-Queens and TSP(a graphical implementation)
• Implementing local search strategies: hill climbing, simulated annealing and genetic algorithms
• Programming assignment

Lesson 4: Adversarial search and games

• Implementing Otello
• Implementing adversarial search algoritms: Minimax and alpha-beta prunning
• Programming assignment

Prerequisite

• Basic knowledge of programming (Python)
• Basic knowledge of data structures and algorithms

After first part:

• You will have a good understanding of basic AI techniques (solving problems using searching)
• You will become a real python programmer and most importantly a real programmer!
• You will see a lot of programming challenges and you will learn how to solve them

Reference