🤖 Artificial Inteligence Fundamentals Laboratory

This is a Python-based laboratory on Artificial Intelligence for university, featuring theoretical concepts and tested solutions.

MIT OpenCourseWare (OCW) Reference

The initial five labs are also available in an unsolved format on MIT OpenCourseWare, accompanied by video lectures and supplementary materials.

Lab Contents Overview

1. Python Basics Revision & Symbolic Algebra
2. Forward Chaining
3. Backward Chaining and Goal Trees
4. Search Algorithms: BFS, DFS, Hill Climbing, A*, Heuristics
5. Game Searches (Mancala, Breakthrough): Alpha-Beta Pruning, Minimax
6. Constraint Satisfaction Problems: Forward Checking, Forward Checking with Propagation Through Singletons (Moose CSP, Map Coloring)
7. Classification: k-Nearest Neighbors, Decision Trees
8. Neural Networks
9. Neural and Convolutional Networks (MNIST, CIFAR10 with visual representation)
10. Bayesian Methods (SMS Spam Filtering)
11. Applied Machine Learning: Naive Bayes, KNN, Logistic Regression Model, Random Forest, Decision Tree, Support Vector Machine, Gradient Boosting, Multi-layer Perceptron, Extra Trees