ML-Diaries

A concise, hands-on collection of machine learning and deep learning experiments and reference implementations maintained by Aaron. The repository focuses on practical, well-documented code that demonstrates core ML/DL concepts and workflows.

Table of contents

• Overview
• Implemented Modules & Status
• Repository structure
• Getting started
• Contributing
• License
• Contact

Overview

ML-Diaries contains compact, reproducible implementations for learning and teaching fundamental ML/DL techniques. The aim is to provide clear code, runnable examples, and brief explanations so readers can quickly understand and reproduce results.

Implemented Modules & Status

Status legend:

• Completed — documented examples available (notebooks and/or code present)
• Partial — partial coverage or examples in progress
• Planned — listed for future work

Repository structure

• Deep Learning/ — Autoencoders, neural nets and related notebooks
  • AE_AutoEncoders/ — AutoEncoders.ipynb
  • Neural networks/ — activation functions notebook, perceptron.py, ANN notebooks
• Foundations/ — core concept notebooks (e.g., ImbalancedLearning, pytorch_intro)
• Machine Learning/ — multiple subtopics
  • Bayesian Learning/ — bayes notebooks, data (train/dev/test)
  • Decision Tree/ — DecisionTrees_ID3Algorithm.ipynb
  • Hidden Markov Model/ — HMM.ipynb
  • SVM/ — hardMarginSVM.ipynb
• README.md — this file

(This listing reflects the current folders & notebooks in the repository.)

Getting started

Prerequisites:

• Python 3.8+ (recommended)
• Typical ML libraries: numpy, pandas, scikit-learn, torch or tensorflow (depending on module)

Quick start:

You can directly download the Notebooks, from github.com [Not too much work--just have to locate it], or if you'd like this way, Here's That:

1. Clone the repository: $ git clone
2. Create and activate a virtual environment: $ python -m venv .venv $ source .venv/bin/activate
3. Install dependencies (example): $ pip install -r requirements.txt
4. Explore notebooks/ and run example scripts.

License

Actually, I've compiled this work from Personal Notes in Class, AI-Generated Help, Different textbooks and sources (Video/Articles on Medium/Substack/YouTube or any other leading platform). So: It's technically a Compilation, use as you wish :)

Contact

Maintained by AaronTM! Feel free to Mail me on aaronmat.work@gmail.com or LinkedIn | Other Social Media Platforms | Or any old fashioned Methods [Messenger Pigeon , Letter, Marathon Runner, Note-taped to a stone, Horsemen => Anything except mobile]