From Y=X to Building a Complete Artificial Neural Network - KDnuggets

At some point, you might have asked yourself, What are the origins of parameters for artificial neural networks? What is the purpose of the weight? What if no bias is used? In this tutorial, we set out to answer those questions by working from the most simple artificial neural network (ANN), to something much more complex. Let's start by building a machine learning model with no parameters--which is Y X. Then, we'll gradually add some parameters to the model until we build a single neuron. This neuron is made to accept one or more inputs. The mathematical representation of the neuron is then mapped to a graphical representation. By connecting multiple neurons, a complete ANN can be created.