APLAB.ACADEMY · INTERACTIVE LEARNING INSTRUMENTS64 TOOLS · 8 COURSES · 97 LESSONS
FIG. 01 — THESIS
Master the
fundamentals.
Through interaction.
Most ML courses ask you to read formulas and watch videos. Here, every lesson is built around a working instrument — a thing you can poke at while you read. Build intuition first, then the math, then the code.
FIG. 01Multi-Head Self-Attention — try a token
INTERACTIVE
YOUR SENTENCE · TYPE TO POKE
INPUT TOKENS · CLICK TO QUERY
ATTENTION FROM "sat" — HEAD 0
1
99
1
0
0
0
The
cat
sat
on
the
mat
Illustrative — stylised attention patterns computed from your sentence, not a trained model. The real engine is in the Attention Microscope.
ATTENTION HEADS
OBSERVATION · PREVIOUS TOKEN
This head looks one step back — each token attends to the token immediately before it. The very first token has nothing prior, so it attends to itself. Induction and copying circuits lean on exactly this.
Figure 1.Live preview from the Transformer Explorer. Click a token, switch heads, and watch the attention pattern change.
§02 · METHOD
Connected Learning, not linear lectures.
Four passes through every concept. Each pass deepens what you already understand.
I.
INTUITION
See it move.
Start with a visualization you can manipulate. No equations yet — just notice patterns.
↳ interact
II.
THEORY
Then formalize.
Once intuition is in place, the math reads as a description of what you already saw.
↳ derive
III.
CODE
Build it yourself.
Implement the concept in a runnable environment. Break it. Fix it. Own it.
↳ execute
IV.
CONNECTIONS
Where else does this live?
Every concept links to its appearances elsewhere — the knowledge graph, not a track.
↳ navigate
§03 · INSTRUMENTS
Working instruments. Each a real idea.
Every visualization is a real, manipulable component — not a video, not a static figure.
FIG. 01VISUALIZATION
Model Training & Parallelism Explorer
Comprehensive tool for exploring training strategies
used in 1 lessonsopen →
FIG. 02INTERACTIVE
AI Agents Explorer
Watch AI agents move, think, and communicate in real-time
used in 1 lessonsopen →
FIG. 03INTERACTIVE
Python Memory Explorer
Deep dive into Python memory management, object model, and CPython internals
used in 1 lessonsopen →
FIG. 04INTERACTIVE
Tokenizer Bench
Same text, four tokenizers. Token chunks, costs, and a step-by-step BPE merge view.
used in 1 lessonsopen →
FIG. 05VISUALIZATION
Gradient Lab
2D classification with a hand-rolled MLP. Step through SGD, watch the decision boundary form.
used in 2 lessonsopen →
FIG. 06VISUALIZATION
Attention Microscope
Inspect synthetic GPT-2-style attention layer by layer, head by head. Ablate heads, watch top-5 candidates shift.
used in 2 lessonsopen →
§04 · CURRICULUM
Eight courses. Foundations to frontier.
Structured paths — but every concept is also a node, reachable from anywhere.
№COURSECATEGORYLESSONSLEVEL
01Python Fundamentals: Programming FoundationsPython Programming·12 lessons·Beginner12Beginner→02Python for Data Science: From Arrays to AnalysisPython Programming·10 lessons·Intermediate10Intermediate→03Python Advanced: Professional Engineering MasteryPython Programming·12 lessons·Advanced12Advanced→04Classical Machine Learning: Supervised Learning FoundationsMachine Learning·15 lessons·Intermediate15Intermediate→05Advanced ML: Unsupervised Learning & ProductionMachine Learning·12 lessons·Advanced12Advanced→06NLP Fundamentals: Core Concepts and ArchitecturesNatural Language Processing·11 lessons·Intermediate11Intermediate→07Advanced NLP: Training & Production Systems★ PREMIUMNatural Language Processing·11 lessons·Advanced11Advanced→08AI Agents: Building Autonomous Intelligent SystemsAI Agents·14 lessons·Advanced14Advanced→