Machine Learning Knowledge Base

Study notes on designing, developing, and deploying ML systems, compiled from the courses, books, and essays listed under Sources. Examples and case studies come from those sources; they are not my own projects.

Read them as a site: https://0trm.dev/mlkb/

The process is split into three stages: Design, Development, and Deployment. The overview walks the whole lifecycle once; each stage then has its own pages.

Scope: classic (predictive) ML systems. LLMs and foundation models are not covered.

Contents

1 · Overview

• 1.1 Introduction
• 1.2 ML Project Lifecycle
• 1.3 ML Project Checklist
• 1.4 MLOps
• 1.5 Case Study: Speech Recognition System

2 · Design

• 2.1 Scoping
• 2.2 Data

3 · Development

• 3.1 Modeling Overview
• 3.2 Validation and Hyperparameter Tuning
• 3.3 Model Baseline
• 3.4 Error Analysis
• 3.5 Prioritizing Improvements
• 3.6 Skewed Datasets
• 3.7 Performance Auditing
• 3.8 Data-centric AI Development
• 3.9 Experiment Tracking

4 · Deployment

• 4.1 Key Challenges in Deployment
• 4.2 Deployment Architecture
• 4.3 Common Deployment Patterns
• 4.4 Reproducibility and CI/CD
• 4.5 Monitoring
• 4.6 Case Study: Defect Inspection in Manufacturing

Appendix

• Templates
• Sources

Building the site locally

pip install -r docs/requirements.txt
sphinx-build -b html docs docs/_build/html

Pushes to main rebuild and deploy the site through .github/workflows/pages.yml.

The favicon is the card file box emoji from Noto Emoji (Apache 2.0).