Skip to content

About

Structured machine learning notes, with mathematical explanations and visual breakdowns of core algorithms - from regression and neural networks to clustering, recommender systems, and reinforcement learning.

Topics

Resources

Contributing

Stars

0 stars

Watchers

1 watching

Forks

Repository files navigation

Machine Learning Notes

Machine Learning Notes

A set of digital notes made from 53 pages of handwritten Machine Learning notes. The handwriting has been typeset, the equations rewritten in LaTeX, and the sketches redrawn as diagrams placed right next to the explanation they support.

Who is it for? University students learning Machine Learning who want short, structured notes for learning and revision.

The notes follow the topics of the source and nothing else. Wherever the handwriting was unclear, or looked like a slip, it is flagged instead of silently fixed — see TRANSCRIPTION_NOTES.md. Text added to help understanding is always marked Additional Explanation.

Learning roadmap

Recommended order of the six modules

  1. Start with supervised learning — everything else builds on its cost functions and gradient descent.
  2. Move to neural networks, which reuse those ideas.
  3. Learn how to evaluate and improve models (bias, variance, error analysis).
  4. Study decision trees and ensembles as the other major family of supervised models.
  5. Continue with unsupervised learning (clustering, anomaly detection).
  6. Finish with recommender systems and reinforcement learning.

Table of contents

Regression and classification: linear and logistic regression, gradient descent, feature scaling, overfitting and regularization.

  1. Linear Regression
  2. Linear Regression with Multiple Features
  3. Feature Scaling
  4. Gradient Descent in Practice
  5. Feature Engineering and Polynomial Regression
  6. Decision Boundary
  7. Logistic Loss, Cost and Gradient Descent
  8. Overfitting
  9. Regularization

Neural networks: layers, activation functions, softmax, vectorization, TensorFlow training steps, backpropagation, Adam.

  1. Neural Networks
  2. Layer Computation (Intuition)
  3. Activation Functions
  4. Multiclass Classification and Softmax
  5. For Loop versus Vectorization (Dense Layer)
  6. TensorFlow and Model Training Steps
  7. Backpropagation versus Gradient Descent
  8. Adam Algorithm and Types of Layers

Train/CV/test sets, model selection, bias and variance, learning curves, error analysis, metrics, transfer learning, deployment.

  1. Train / Cross-validation / Test Procedure
  2. Model Selection
  3. Bias and Variance
  4. Learning Curves and Debugging a Learning Algorithm
  5. Adding Data, Data Augmentation and Data Synthesis
  6. ML Development and Error Analysis
  7. Precision, Recall and the F1 Score
  8. Transfer Learning
  9. ML Project Cycle and Deployment

Decision trees, entropy, information gain, one-hot encoding, regression trees, random forests, XGBoost.

  1. Decision Trees
  2. Entropy as a Measure of Impurity
  3. Information Gain
  4. One-Hot Encoding
  5. Regression Trees
  6. Sampling with Replacement and the Random Forest Algorithm
  7. XGBoost (eXtreme Gradient Boosting)
  8. Decision Trees versus Neural Networks

K-means clustering, choosing K, the Gaussian distribution and anomaly detection.

  1. Clustering and K-Means
  2. K-Means Cost Function and Random Initialization
  3. Choosing the Value of K (Elbow Method)
  4. Gaussian (Normal) Distribution
  5. Anomaly Detection (Intuition) and Choosing Features
  6. Developing and Evaluating Anomaly Detection Systems

Collaborative and content-based filtering, retrieval and ranking, return, policy and the Q function.

  1. Recommender Systems: Notation
  2. Collaborative Filtering versus Content-Based Filtering
  3. Collaborative Filtering: Cost Function and Gradient Descent
  4. Collaborative Filtering with Binary Labels
  5. Mean Normalization
  6. Finding Related Items
  7. Content-Based Filtering with Deep Learning
  8. Retrieval and Ranking
  9. Reinforcement Learning: Return and Discount Factor
  10. Policy and the State-Action Value Function (Q)

Repository features

  • Digitised notes — every page of the handwritten PDF is accounted for.
  • Mathematical equations — KaTeX/LaTeX equations that render on GitHub.
  • Embedded visualisations — SVG diagrams and Matplotlib figures inside each topic page.
  • Structured learning sequence — pages reordered by prerequisite, not by notebook order.
  • Student-friendly explanations — every topic ends with a Detailed Explanation (intuition, worked examples, common mistakes), clearly labelled as an addition to the handwritten source.
  • Source audit — TRANSCRIPTION_NOTES.md lists unclear handwriting, apparent errors and every added explanation.

Navigation

Optional: browse as a website

The same Markdown files can be viewed as a dark-themed documentation site (Midnight Lavender palette, search, KaTeX):

pip install -r requirements.txt
bash scripts/serve_site.sh          # opens http://127.0.0.1:8000

Regenerating figures

pip install numpy matplotlib
python scripts/make_figures.py      # assets/figures/*.png
python scripts/make_diagrams.py     # assets/diagrams/*.svg
python scripts/build_indexes.py     # module READMEs, this README, mkdocs.yml

Colour palette: background #171821, cards #2C2B40, accent #A78BFA / #E89BB5, maths #EAC477, success #91C7A5.

About

Structured machine learning notes, with mathematical explanations and visual breakdowns of core algorithms - from regression and neural networks to clustering, recommender systems, and reinforcement learning.

Topics

Resources

Contributing

Stars

0 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages