AI Learning Handbook

AI, Systems, and Structured Thinking.

A structured space for mastering artificial intelligence — deliberately, deeply, and without noise.

How to Use This Site

  1. 1.Start with the Roadmap.
  2. 2.Study phase by phase.
  3. 3.Use articles to deepen understanding.
  4. 4.Build and iterate.

Why This Exists

The emphasis here is on depth over noise. Structured mastery over scattered tutorials. Long-term learning over quick wins. Clarity over speed. This site exists as a place to document that approach — deliberately, and without the usual hype.

AI Mastery Roadmap

1 / 5
1

Foundation

4–6 weeks · ~40–50 hours

Get from zero to running Python and writing scripts. Variables, loops, functions, and a clear idea of what machine learning is.

Key topics

  • Install Python 3, VS Code, and set up your environment
  • Variables, types, conditionals, loops, functions
  • Lists, dicts, and basic data structures
  • Small projects (calculator, text game, data parsing)
  • Intro: supervised vs unsupervised, training vs inference
2

Math + Machine Learning

Months 1–3 · ~130 hours

Linear algebra, probability, and calculus foundations. Then ML from scratch: linear regression, logistic regression, basic optimization. No black boxes.

Key topics

  • Linear algebra: vectors, matrices, dot products, matrix multiplication
  • Probability: distributions, Bayes, expectation, variance
  • Calculus: derivatives, gradients, chain rule
  • Andrew Ng Machine Learning (Coursera) or equivalent
  • Implement linear regression and logistic regression from scratch
  • Gradient descent and normal equation
3

Deep Learning

Months 4–6 · ~130 hours

Neural networks, backpropagation, CNNs, attention, and transformers. Build implementation skills, use PyTorch/TensorFlow, and start reading papers.

Key topics

  • Neural nets: forward pass, backpropagation, activation functions
  • CNNs: convolutions, pooling, ResNet-style architectures
  • Attention mechanism and transformer architecture
  • PyTorch or TensorFlow — build and train models
  • Paper reading: one paper per 2 weeks, implement key ideas
  • Stanford CS231n and DeepLearning.AI specialization
4

Specialization & Systems

Months 7–9 · ~130 hours

Deep dive into one track (NLP, CV, or RL). Add learning theory, deployment basics, and build a substantial project with clear documentation.

Key topics

  • One track: NLP, Computer Vision, or Reinforcement Learning
  • Learning theory: bias-variance, overfitting, generalization, regularization
  • Systems: model deployment, FastAPI, basic MLOps
  • Paper reading: 2–3 papers per month in your track
  • Substantial project: replication or novel implementation
  • Write a clear technical report (5–10 pages)
5

Advanced Mastery

Months 10–12 · ~130 hours

Paper writing, rigorous replications, and advanced topics. Consolidate knowledge and produce work that demonstrates mastery. Capstone project.

Key topics

  • Rigorous replication of 1–2 key papers in your specialization
  • Paper writing: clear problem, method, experiments, analysis
  • Consolidation: review full curriculum, fill gaps
  • Capstone: one major project or replication
  • Documentation, code quality, reproducibility
  • Optional: contribute to OSS, write blog posts
View full roadmap →

Latest Writing

All articles →