Artificial Intelligence Introduction

About ✍️

The repository contains 7 solutions to tasks (from scratch) related to Artificial Intelligence (AI). The developed notebooks deal with basic concepts concerning artificial neural networks, decision trees or reinforcement learning, among others.

Tasks 📋

1. Gradient Descent - Explore the implementation of the gradient descent algorithm, test it on two selected functions, and visualize the gradient steps.
2. Genetic Algorithm - Dive into a genetic algorithm with mutation, roulette selection, single-point crossover, and generational succession.
3. Minimax with Alpha-Beta Pruning - Implement the minimax algorithm with alpha-beta pruning and apply it to a game of tic-tac-toe.
4. ID3 Decision Tree - Create a decision tree using the ID3 algorithm with a maximum tree depth constraint, tested on the Tic-Tac-Toe Endgame dataset.
5. Two-Layer Perceptron - Develop a two-layer perceptron and train it to represent a given function, describing the Laplace distribution.
6. Q-Learning Algorithm - Implement the Q-learning algorithm and apply it to solve the problem of Cliff Walking.
7. Bayesian Network - Construct a Bayesian network and study the effect of one piece of information on another.

How to run? 🏃

1. Download repository

   git clone https://github.com/kzaleskaa/artificial-intelligence-introduction
   cd artificial-intelligence-introduction
   

2. Create your environment and activate it

   $ python -m venv venv

3. Install requirements

   $ pip install -r .\requirements.txt