← 🧬 Biology

🧠 Neural Net

Task
Epoch 0
Loss (MSE)
Accuracy
Predictions
Neg weight Pos weight High act
Left: network diagram · Right: decision boundary (click to test a point)

🧠 Neural Network — Backpropagation

A two-layer neural network trains live on XOR, circle or spiral classification boundaries. Watch weights change as edges, activations glow as nodes, and the decision boundary evolves in real time.

🔬 What It Demonstrates

Forward pass computes activations through layers. Backpropagation computes gradients of the loss with respect to each weight. Gradient descent updates weights to reduce error.

🎮 How to Use

Pick a dataset (XOR, circle, spiral). Watch training progress — the decision surface morphs to classify points correctly. Adjust learning rate and hidden neurons.

💡 Did You Know?

Backpropagation was popularised by Rumelhart, Hinton and Williams in 1986, but the core idea (reverse-mode automatic differentiation) dates to Seppo Linnainmaa's 1970 master's thesis.