Apache Spark Deep Learning Cookbook

Getting ready

A cursory understanding of the building blocks of a simple neural network is helpful in understanding this section and the rest of the chapter.  Each neural network has inputs and outputs.  In our case, the inputs are the height and weight of the individuals and the output is the gender.  In order to get to the output, the inputs are multiplied with values (also known as weights: w1 and w2) and then a bias (b) is added to the end.  This equation is known as the summation function, z, and is given the following equation:

z = (input1) x (w1) + (input2) x (w2) + b

The weights and the bias are initially just random generated values that can be performed with numpy. The weights will literally add weight to inputs by increasing or ...