The correct answer is: B. nonlinear functions.
Neural networks are made up of many simple processing units called neurons. Each neuron takes in a number of inputs, applies a nonlinear function to them, and then outputs the result. The nonlinear function is what allows neural networks to learn complex patterns.
Linear functions are functions that take in a number of inputs and produce a linear combination of those inputs. This means that the output of a linear function is simply a weighted sum of the inputs. Linear functions are not very good at learning complex patterns, because they can only represent a limited number of possible functions.
Nonlinear functions, on the other hand, can represent a much wider range of possible functions. This is because nonlinear functions can take into account the relationships between the inputs. This allows neural networks to learn more complex patterns than linear functions.
In conclusion, neural networks are complex nonlinear functions with many parameters. The nonlinear functions allow neural networks to learn complex patterns, which is why they are so powerful.