Machine Learning MOC

Welcome to the Machine Learning Map of Content. This dashboard organizes notes logically to provide structured learning paths and rapid discovery.

Core Concepts & Foundations

• Glossary - Foundational machine learning definitions (Bias, Variance, etc.).
• Machine Learning Domains - Breakdown of ML problem types (Classification, Regression, Unsupervised).
• Metrics and Model Evaluation - Guide on evaluating models, bias/variance tradeoff, and regularization.
• Loss Functions - How models measure error (MSE, Cross-Entropy).
• Linear Classifiers - Notes on linear models, hyperplanes, and decision boundaries.

Math for Machine Learning

Deep dive into the mathematical foundations required for ML, located in the Math/ directory.

• 0. Glossary (ML Math)
• 1. Probability
• 2. Linear Algebra
• 3. Calculus
• 4. Bayesian Decision Theory
• 5. Determinants
• 6. Fourier Transform
• 7. Chaos Theory
• 8. Law of Large Numbers
• 9. Vector Calculus
• 10. Vector Norms

Data Preparation

• Exploratory Data Analysis - The crucial first step of inspecting and understanding your data.
• Scaling Techniques - Methods for normalization and when to use them.

Algorithms & Models

Deep dives into specific algorithms, located in the Algorithms/ directory.

Linear & Parametric Models

• Linear Regression
• Logistic Regression
• Polynomial Regression
• Least-Square Classification
• Fisher’s Linear Discriminant
• Rosenblatt’s Perceptron
• Gradient Descent

Tree-Based & Ensemble Methods

• Decision Trees
• Random Forest
• Bagging
• Boosting

Support Vector Machines & Non-Parametric

• Support Vector Machines
• k-Nearest Neighbors

Bayesian Methods

• Bayesian Decision Methods
• Bayesian Networks

Neural Networks & Deep Learning

• Neural Networks
• Convolutional Neural Networks
• Activation Functions

Unsupervised Learning (Clustering & PCA)

• k-Means
• Hierarchical Clustering
• Locally Adaptive Clustering (LAC)
• Mixtures of Gaussians
• Principal Component Analysis (PCA)
• Singular Value Decomposition
• Self-organizing Map

Reinforcement Learning

Detailed domain dashboard: Reinforcement Learning MOC

• Reinforcement Learning - The agent-environment interaction loop.
• Markov Decision Processes - Mathematical framework (States, Actions, Transitions).
• Q-Learning - Off-policy value-based learning.
• Deep Reinforcement Learning - Scaling RL with Neural Networks.
• Dynamic Programming - The foundational framework for solving MDPs.

Applications

• Recommendation Systems
• Learning To Rank
• Anti-Bot Machine Learning - How ML is used to detect and mitigate automated agents.
• Agentic Information Traversal - Benchmarks and tools for measuring how agents navigate web pages and knowledge graphs.

---

To Research / Inbox

(Drop new concepts or terms you want to research here as unlinked wiki-links, e.g., [[Transformers]])