Latent

Neural network playground

Train real neural networks in your browser. Change depth, width, activation, and learning rate, and watch every neuron and the loss curves respond.

IntermediateExplained in Training a network

Neural network playground

Train a real network in your browser. Shading shows its prediction everywhere; small squares show what each neuron computes.

Blue regions are predicted blue, orange regions orange. Paler means less sure.

Tap a neuron to show its output full size. Lines are weights: red positive, blue negative, thicker is larger.

Data
0.20
Hidden layers
4
Activation
0.03
Optimizer
Batch size
Epoch0
Training loss0.000
Test loss0.000
Test accuracy0%
Parameters0

Try this

  • Train the default circle, then set hidden layers to 0. A network with no hidden layer can only draw a straight line.
  • Try the spiral with ReLU, 2 layers of 8, and a learning rate near 0.01.
  • Set noise to 1 with 8 neurons per layer and train for a few hundred epochs. Watch test loss rise while training loss falls.
  • Tap any neuron in the diagram to see what it computes.

Try "embedding", "softmax", "overfitting", or "backpropagation".