Welcome to VizLearn

See how AI and algorithms
actually work

Every module is a visualisation you can drive, running the real computation — machine learning, deep learning, algorithms, and the maths underneath them. No jargon, no account, nothing gated.

Start the Learning Path Browse all 240 modules
229 Visual Modules
9 Guided Tracks
100% Free Forever
No Login, No Setup

Start here

The first page of six tracks

Each of these is the opening module of its track - the one that assumes the least.

Maths

47 modules

Machine Learning

45 modules

Deep Learning

46 modules

Algorithms

41 modules

NLP

41 modules

Computer Vision

47 modules

Database

42 modules

Gen AI

52 modules

Python

46 modules

Async Python

5 modules

Pydantic

30 modules

FastAPI

26 modules

NumPy

20 modules

pandas

26 modules

matplotlib

22 modules

scikit-learn

23 modules

Interview Questions

49 modules

Every track

608 modules across 17 tracks

Distance from the centre is the number of modules in that track. Point at a spoke, or tab through them, to pull one out - each is a link to that track.

Modules per trackOne spoke per track; distance from the centre is that track's module count. Every spoke is a link, and the same numbers are in the table beside the chart.15304560Gen AI52Interview49Computer Vision47Maths47Deep Learning46Python46Machine Learning45Database42Algorithms41NLP41Pydantic30FastAPI26pandas26scikit-learn23matplotlib22NumPy20Async Python5

Hover a spoke for its count

Modules per track
TrackModules
Gen AI52
Interview49
Computer Vision47
Maths47
Deep Learning46
Python46
Machine Learning45
Database42
Algorithms41
NLP41
Pydantic30
FastAPI26
pandas26
scikit-learn23
matplotlib22
NumPy20
Async Python5

How it works

Three steps, then you are just using it

No account, no install, nothing gated. Open a page and it runs.

1

Pick the idea, not the chapter

Every module is one concept with one visualisation. There is no chapter to finish before it makes sense, and no order you have to arrive in.

2

Drive it until it breaks

The controls are the point. Set k to 1 and watch KNN overfit, push the learning rate until descent diverges. Understanding usually arrives at the failure, not the happy path.

3

Read the code that did it

Where it helps, the same page carries a Python editor running the real thing in your browser. Change a line, run it, see the output move.

Questions

The ones worth answering up front

Is it actually free?

Yes, and there is nothing to sign up for. No account, no trial, no email wall.

Does the Python really run?

It runs CPython compiled to WebAssembly, in a worker thread in your browser. Nothing is uploaded and nothing is executed on a server.

Does it work offline?

The site installs as an app and caches what you have opened, so pages you have already visited keep working without a connection.

Who is it for?

Anyone who has read the definition and still cannot picture the thing. It assumes no maths degree and leaves nothing as an exercise for the reader.

Open one and push a slider

That is the whole pitch. 608 modules, all of them running the real computation, none of them asking you for anything first.