How to Use This Site

You've already seen the pitch on the homepage — real, computed, interactive visualizations instead of static diagrams. This page is shorter: how the site is put together, and where to actually go next.

How a page is built

Almost every page in this curriculum follows the same shape: intuition, then visualization, then math, then code. A plain-language explanation of why something works, backed immediately by a live component you can manipulate (not a screenshot), then the formal math once you already have a mental model to hang it on, then real code once the math is concrete. Attention & Transformers is the fullest example of this end to end — type a sentence into it and watch real attention weights compute, the same live component that's embedded on the homepage.

Finding your way around

• Sidebar (left) — every section, organized by topic (Mathematics for AI, Machine Learning, Deep Learning, LLMs & GenAI, Agents, MLOps, and more), in roughly the order most people learn them. Collapse it for a wider reading column with the ‹ toggle.
• Table of contents (right) — every heading on the current page, for jumping around a long one.
• Search (Cmd+K / Ctrl+K) — the fastest way in if you already know what you're looking for.
• Progress (top nav) — click Mark as understood on any page to track it here, tracked locally in your browser, no account needed. Marking a page also starts a simple spaced-repetition schedule for it (review reminders at 1, 3, 7, 14, and 30 days) — the Progress page's Due for Review section surfaces whatever's worth a refresh, whenever you check back in.

Where to start

There's no single mandated order — pick whichever matches you:

• New to ML entirely? Start with Mathematics for AI or go straight into Machine Learning and backfill math as it comes up.
• Comfortable with the fundamentals, here for LLMs and agents? Jump to LLMs & GenAI or Agents directly.
• Just want to play with something interactive first? Visual Lab is nothing but live, parameter-driven visualizations — no prerequisite reading.
• Want a guided, end-to-end path? The Neural Mastery Roadmap sequences every section from zero to job-ready, or see Suggested Paths for a shorter route toward a specific role.
• Prefer to learn by writing code? Practice Problems are short, focused exercises — implement a function yourself in a real, in-browser Python sandbox, run it against real test cases, then reveal a reference solution.
• Prepping for interviews specifically? Interview Prep covers strategy for every round, and the Q&A Quick Reference is a click-to-reveal cram sheet for the rapid-fire breadth round.