Lesson 1: Understanding a Single Neuron
A neuron takes an input, multiplies it by a weight, adds a bias, and applies an activation function.
Formula: output = activation(input × weight + bias)
Weighted Sum: 0.50
Output: 0.62
Lesson 2: Multi-Layer Neural Network
A neural network consists of layers of neurons. Each neuron in a layer connects to all neurons in the next layer. The network learns by adjusting weights through backpropagation using multiple training examples.
Training Data
Add multiple input-output pairs for the network to learn from
Training Controls
Backpropagation in Action
1. Forward Pass
Input → Hidden → Output
Current Output: 0.00
Target: 0.00
2. Calculate Error
Error = Target - Output
Error: 0.00
Avg MSE: 0.00
3. Compute Gradients
How much each weight contributed to error
Avg Gradient: 0.00
4. Update Weights
Weight -= Learning Rate × Gradient
Training Steps: 0
Epochs: 0
Recent Weight Changes
Lesson 3: Handwritten Digit Recognition (MNIST)
Train a neural network to recognize handwritten digits (0-9). Draw a digit and see the network predict it!
Training Progress: Not trained
Epoch: 0 / 10
Accuracy: 0%