The AI Cheatsheet Curriculum That Starts with Calculus

What it does

This repository collects existing cheatsheets and quick-reference PDFs for artificial intelligence and machine learning into a single, browsable hierarchy. The folders follow a visual roadmap that begins with calculus and computer architecture, winds through Python, SQL, and data cleaning, and ends at deep learning, reinforcement learning, and Git. It is purely a curation effort—there is no original code, just aggregated documents and a Google Drive mirror for bulk download.

The interesting bit

The organizer treats AI literacy as a full-stack discipline: you get automata theory and complexity theory right alongside NumPy and Matplotlib references. It is the kind of syllabus you might sketch if you were trying to turn a computer-science undergraduate into a production ML engineer in one semester.

Key highlights

• Eighteen topic folders spanning mathematics, C++, Python, data structures, SQL, data visualization, and core AI/ML subjects
• Includes niche foundational layers like computer architecture, automata theory, and mathematical logic
• Curated around a visual AI/ML roadmap that suggests a learning order
• Google Drive mirror available for offline bulk access
• Covers practical corners often ignored in academic roadmaps: data-cleaning checklists, feature-engineering guides, MLOps, and evaluation metrics

Caveats

• The README duplicates the 06- folder number for both Automata theory and Complexity theory, suggesting light maintenance
• Content is third-party and aggregated; originality and licensing of individual cheatsheets are unspecified
• Purely static reference material—no interactivity, code, or searchability beyond GitHub’s file browser

Verdict

Grab this if you are a student or self-taught developer building a personal AI curriculum and want a structured folder of PDF quick-reference guides. Skip it if you are looking for executable notebooks, original tutorials, or a unified interactive reference.