Learning OpenCV 4 Computer Vision with Python 3 - Third Edition

Understanding the layers of a neural network

Here is a visual representation of a neural network:

As the preceding diagram shows, there are at least three distinct layers in a neural network: the input layer, the hidden layer, and the output layer. There can be more than one hidden layer; however, one hidden layer is enough to resolve many real-life problems. A neural network with multiple hidden layers is sometimes called a deep neural network (DNN).

If we are using an ANN as a classifier, then each output node's output value is a confidence score for a class. For a given sample (that is, a given set of input values), we want to know which ...