In corporate projects, there always comes the point when a problem that seems impossible to solve hits you. At that point, you try everything you learned, but it doesn't work for what's asked of you. Your team or customer begins to look elsewhere. It's time to react.
In this chapter, an impossible-to-solve business case regarding material optimization will be implemented successfully with an example of a feedforward neural network (FNN) with backpropagation.
Feedforward networks are the building blocks of deep learning. The battle around the XOR function perfectly illustrates how deep learning regained popularity in corporate environments. The XOR FNN illustrates one of the critical functions of neural networks: classification. Once information becomes classified into subsets, it opens the doors to prediction and many other functions...