This repository contains the completed projects for Harvard University's CS50's Introduction to Artificial Intelligence with Python (CS50AI).
The projects collectively demonstrate proficiency in core AI fields, including classical search, knowledge representation, uncertainty, machine learning, deep learning (neural networks), and natural language processing. Each project corresponds to a lecture and applies specific AI algorithms to solve a complex computational problem.
The portfolio is structured around the foundational domains of Artificial Intelligence:
| Domain | Projects Included | Core Technologies |
|---|---|---|
| Classical Search | Degrees of Separation (P0) | Breadth-First Search (BFS), Graph Traversal |
| Knowledge & Logic | Knights and Knaves (P1), Minesweeper AI (P2) | Propositional Logic, Logical Inference, Constraint Satisfaction |
| Probabilistic AI | PageRank (P3) | Markov Chains, Monte Carlo Sampling, Iterative Optimization |
| Machine Learning | Shopping (P4) | K-Nearest Neighbors (KNN), Classification, Model Evaluation |
| Deep Learning | Traffic (P5) | Convolutional Neural Networks (CNNs), TensorFlow/Keras |
| Natural Language Processing | Question Answering (P6) | TF-IDF, Text Ranking, Information Retrieval |
The table below provides a quick reference for each project, linking the academic concept to the practical application.
| Project No. | Lecture Topic | Project Name | Core Algorithm(s) |
|---|---|---|---|
| P0 | Search | Degrees of Separation | Breadth-First Search (BFS) |
| P1 | Knowledge | Knights and Knaves | Propositional Logic, Model Checking |
| P2 | Uncertainty | Minesweeper AI | Logical Inference, Set Theory |
| P3 | Optimization | PageRank | Markov Chains, Monte Carlo Sampling |
| P4 | Learning | Shopping Intention | K-Nearest Neighbors (KNN) |
| P5 | Neural Networks | Traffic Sign Classification | Convolutional Neural Networks (CNN) |
| P6 | Language | Question Answering | TF-IDF, Semantic Ranking |