The problem in this simple NN does not present you with the internals, so there is no “internal mechanism” to be observed, there are certainly neural networks that try to figure out the internals of the problem or guess the solution (like your black box or autoencoders) , but in this simple case the answer is static and known by us, the NN still has to learn it. It is one of those odd things in Data Science and NN, you are presented with solved or partially solved problems (usually test data set) and then derive related solutions for future identification or problem solving.

Written by

AI, Software Developer, Designer :

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store