Defining a CNN

This section describes the basic components of a CNN. 01_CNN_SRATEGY_MODEL.py will illustrate the basic CNN components the chapter used to build the case study model for a food-processing conveyor belt. CNNs constitute one of the pillars of deep learning (multiple layers and neurons).

In this chapter, a Keras neural network written in Python will be running on top of TensorFlow. If you do not have Python or do not wish to program, the chapter is self-contained with graphs and explanations. 

Defining a CNN

A convolutional neural network takes an image, for example, and processes it until it can be interpreted. 

For example, imagine you have to represent the sun with an ordinary pencil and a piece of paper. It is a sunny day, and the sun shines very brightly, too brightly. You put on a special pair of very dense sunglasses. Now you can look at the sun for a few seconds. You have just applied a color reduction filter, one of the first operations of a convolutional network. Then you...