Loading subject…
Convolutional Neural Network (CNN)
A neural network designed for data with spatial structure, above all images.
Feature map
The grid of values produced when one filter is applied at every position of a layer's input. Each value records how strongly that filter's pattern matched at that position.
Loss function
The function that measures how wrong a model's prediction is on a training example. Training adjusts the weights in the direction that reduces it.
Spatial hierarchy
The layered progression of features a convolutional network learns, from edges and colour gradients in early layers to textures, object parts and whole objects in later ones.