As detailed in Chapter 4, Concrete Quality Prediction Using Deep Neural Networks, artificial neural networks (ANNs) are inspired from biological neural networks: starting from the mechanisms regulating natural neural networks, they intended to simulate human thinking. They are used to estimate or approximate functions that may depend on a large number of inputs, many of which are often unknown. ANNs are generally introduced as interconnected neuron systems, among which an exchange of messages takes place. Each connection has a related weight; the value of the weight is adjustable based on experience, and this makes neural networks an instrument that's adaptable to the various types of input and having the ability to learn, as depicted in the following diagram:
ANNs define the neuron as a central processing unit (CPU), which performs a mathematical...