- 122 Downloads
This chapter introduces a few daily life problems, which lead to the concept of abstract neuron and neural network. They are all based on the process of adjusting a parameter such as a rate, a flow, or a current that feeds a given unit (tank, transistor, etc.), which triggers a certain activation function. The adjustable parameters are optimized to minimize a certain error function. At the end of the section we shall provide some conclusions, which will pave the path to the definition of the abstract neuron and neural networks.