Once the feedforward network for solving the XOR problem is built, it will be applied to a material optimization business case. The material-optimizing solution will choose the best combinations of dimensions among billions to minimize the use of a material with the generalization of the XOR function. First, a solution to the XOR limitation of a perceptron must be fully clarified.
The XOR limit of the original perceptron
XOR and linearly separable models
In the academic world, like the private world, competition exists. Such a situation took place in 1969. Minsky and Papert published Perceptrons. They proved mathematically that a perceptron could not solve an XOR function. Fortunately, today the perceptron and its neocognitron...