Machine Learning & Deep Learning Notes

Welcome to my repository of notes, resources, and insights on Machine Learning (ML) and Deep Learning (DL). This project serves as a personal knowledge base where I document my learning journey while I complete my Master's in CS with AI. Feel free to explore, contribute, or use this as inspiration for your own learning path.

About This Project

This repository is a living document of my studies and experiments in ML and DL. It includes:

• Summaries of core concepts (e.g., supervised learning, neural networks, etc.).
• Code snippets and examples from my practice.
• Resources, such as books, tutorials, papers, and tools.

The goal is to create an accessible hub for my notes.

Table of Contents

• Machine Learning & Deep Learning Notes
  • About This Project
  • Table of Contents
  • Getting Started
    • Prerequisites
  • Topics Covered
  • Resources
  • How to Use This Repo
  • Contributing

Getting Started

If you're new to ML/DL or just browsing, here’s how to navigate this repo:

• Check the Topics Covered section for an overview of what’s included.
• Explore the notes/ folder for detailed markdown files on specific topics.
• Look at the code/ folder for practical examples (if applicable).
• See the Resources section for recommended learning materials.

Prerequisites

To follow along with any code examples:

• Basic knowledge of Python.
• Familiarity with libraries like NumPy, Pandas, Scikit-learn and PyTorch.
• A local environment with Jupyter Notebook or a similar IDE.

Topics Covered

Here’s a snapshot of the topics I’m exploring (this will grow over time):

• Machine Learning Basics
  • Supervised vs. Unsupervised Learning
  • Regression, Classification, Clustering
  • Overfitting and Regularization
• Deep Learning
  • Neural Networks and Backpropagation
  • Convolutional Neural Networks (CNNs)
  • Recurrent Neural Networks (RNNs)
• Practical Skills
  • Data Preprocessing
  • Model Evaluation Metrics
  • Hyperparameter Tuning
• Advanced Topics (to be added)
  • Transformers
  • Generative Adversarial Networks (GANs)
  • Reinforcement Learning

Resources

A collection of resources I’ve found helpful:

• Books
  • Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow by Aurélien Géron
  • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
• Online Courses
  • CS231n: Convolutional Neural Networks for Visual Recognition (Stanford)
  • Deep Learning Specialization by Andrew Ng (Coursera)
• Tutorials & Blogs
  • Towards Data Science (Medium)
  • PyTorch Tutorials
• Tools
  • Jupyter Notebook
  • Google Colab
  • Kaggle (for datasets, competitions and free-use GPUs)

More resources will be added as I discover them!

How to Use This Repo

1. Browse Notes: Open the notes/ folder. I will produce my notes as .ipynb files containing code examples.
2. Run Code: Check the code/ folder for scripts or notebooks (e.g., .ipynb files) to see implementations.
3. Contribute: If you have suggestions or corrections, see the Contributing section.
4. Fork It: Feel free to fork this repo and adapt it for your own learning journey!

Contributing

I’d love feedback or contributions! If you’d like to add a resource, fix a typo, or suggest a topic:

1. Fork this repository.
2. Create a new branch (git checkout -b feature/add-notes).
3. Make your changes and commit them (git commit -m "Added notes on CNNs").
4. Push to your branch (git push origin feature/add-notes).
5. Open a Pull Request.

Please keep contributions clear, concise, and relevant to ML/DL learning.