Building and training a CNN will only succeed with hard work at choosing the model, the right dataset, and hyperparameters. Convolutions, pooling, flattening, dense layers, activations, and optimizing parameters (weights and biases) form solid building blocks to train and use a model.
Training a CNN to solve an everyday industrial problem helps sell AI to a manager or a sales prospect. In this case, using the model to help a food-processing factory solve a conveyor belt productivity problem takes artificial intelligence a step further into everyday corporate life.
Saving the model provides a practical way to use it by loading it and applying it to new images to classify them. This chapter concluded after we had trained and saved the model.
Chapter 10, Applying Biomimicking to Artificial Intelligence, will dive deeper into how neural networks were inspired by human neural...