// itseyland.com

Learn machine learning
by playing with it.

A collection of interactive demonstrations, from a single artificial neuron to a convolutional network reading handwritten digits. Every page runs in your browser — change the inputs and watch the math respond.

y = σ( w · x + b )
Layer 0

Algorithmic thinking

Tower of Hanoi

Step through a recursive algorithm as it solves the Tower of Hanoi puzzle, one disk move at a time.

Open demo →
Hanoi.html
Layer 1

The artificial neuron

McCulloch–Pitts Neuron

Explore the math behind the first model of an artificial neuron: binary inputs, weights and a firing threshold.

Open demo →
MPN.html
Layer 2

Learning through optimization

Gradient Descent

Watch basic gradient descent walk downhill on a loss surface, and see how the learning rate changes its path.

Open demo →
Gradient.html

Backpropagation

Follow gradient descent through a network as errors flow backward and every weight gets its update.

Open demo →
Descent.html
Layer 3

Computer vision

Convolution Kernels

Apply different kernels — edge detectors, blurs, sharpeners — and see the feature maps a CNN layer produces.

Open demo →
CNN.html

MNIST Digit Classifier

Draw a digit and let a CNN trained on the MNIST dataset classify it, with confidence for each class.

Open demo →
MNIST.html