Mastering Predictive Analytics with R

The artificial neuron

Using our biological analogy, we can construct a model of a computational neuron, and this model is known as the McCulloch-Pitts model of a neuron:

Note

Warren McCulloch and Walter Pitts proposed this model of a neural network as a computing machine in a paper titled A logical calculus of the ideas immanent in nervous activity, published by the Bulletin of Mathematical Biophysics in 1943.

This computational neuron is the simplest example of a neural network. We can construct the output function, y, of our neural network directly from following our diagram:

The function g() in our neural network is the activation function. Here, ...