4 input image Weights W₁ Layer 1 Weights W₂ Layer 2 Predictions Y' scores per class forward pass →

The network sees a raw image of a handwritten digit. Pixel values flow into the first layer, get transformed by weights, pass to the next layer, and eventually produce a score for each possible class (0–9).

At the start of training the weights are random, so the predictions will be garbage — that's fine. The whole point of training is to fix them.

1 / 6