February 2019
Beginner to intermediate
308 pages
7h 42m
English
Images are represented in computers as a group of pixels, with each pixel having its own intensity (value between 0 and 255). Color images have three channels (red, green, and blue) while grayscale images have only one channel.
All convolutional neural network consists of convolution layers, pooling layers, and fully connected layers.
The convolutional and pooling layers are responsible for extracting spatial characteristics from the images. For example, when training a CNN to identify images of cats, one such spatial characteristic would be the pointy ears of cats.