I was reading about convolutional neural networks and I came across such an explanation : "Consider detecting features in human face. The earlier layers of neural networks learn coarse features such as edges in the images and the latent layers learn more complex ( finer) features such as eyes, nose and etc".
Consider detecting features in human face. The earlier layers of neural networks learn coarse features such as edges in the images and the latent layers learn more complex ( finer) features such as eyes, nose and etc
I am wondering why this is a true statement, namely how can we know that a neural network first starts by learning primitive features and then learns complex features. Could you please explain ?