MAS473: Introduction to Artificial Intelligence with Mathematics

Welcome to the repository for the "MAS473: Introduction to AI with Math" course at KAIST. This repository serves as the central hub for all resources associated with the course, including homework assignments, lecture slides, Jupyter Notebook files with Python code examples, and materials for the final project and exam. The resources here will help you gain a practical understanding of artificial intelligence concepts through mathematical approaches.

📚 Repository Structure

• Final Exam: This directory hosts the materials for the final exam of MAS473, presenting a detailed set of problem sets along with their solutions to prepare effectively for the examination.

• Final Project: Here, you will find the final project requirements and my report file, which delineates the process, methodology, and findings of the project. The train/test files required for the course's final project will give you a head-start in working on your project with all necessary data at your fingertips.

• Homeworks: This folder contains all homework materials distributed throughout the course. Each assignment is crafted to reinforce the concepts taught in lectures and to foster a practical understanding of AI with mathematical approaches.

• Lecture Slides: This section has all the slides used in lectures, laying down the theoretical foundations of the AI concepts discussed in the course.

• Jupyter Notebook Files: You will find the following Jupyter Notebook files that detail various AI concepts and Python implementations:

  • CNNs.jpynb: Deep dive into Convolutional Neural Networks (CNNs) and Fully Connected Neural Networks (FCNNs).
  • Decision_Trees.jpynb: Understanding the mechanism of Decision Trees in AI.
  • GNB_and_PCA.ipynb: Learn about Gaussian Naive Bayes Classifier and Principal Component Analysis (PCA).
  • K_means_clustering_and_GMM.ipynb: A comprehensive guide to K-means clustering and Gaussian Mixture Models (GMM).
  • Linear_Regression.ipynb: Explores the concepts of Linear Regression and Classification.
  • Logistic_Regression_and_SVM.ipynb: A detailed overview of Logistic Regression and Support Vector Machines (SVM).
  • MAS473_Recitation_Basics.jpynb: Get to grips with the basics of Numpy and PyTorch library in this starter notebook.
  • Sarsa_and_Q-Learning.ipynb: Delve into reinforcement learning with Sarsa and Q-learning scripts.

🛠️ Installation and Usage

To access the materials in this repository, follow the instructions below:

1. Clone the repository to your local system using the following command:

git clone https://github.com/anar-rzayev/Artificial-Intelligence-in-Mathematics.git

2. Navigate to the cloned repository's directory:

cd Artificial-Intelligence-in-Mathematics

3. Open the Jupyter Notebook files to access the Python code examples and tutorials:

jupyter notebook