I may have missed something. In the previous course, we had specific training data and calculated the cost functions to generate our models. Then in this (2nd) course, we are programming neural networks. It seems like we are simply feeding training numbers into the neural network. But how does the neural network get trained, and how does it know how to split the work up between nodes?
OK, I jumped ahead. The last thing Mr. Ng said in the last video for week 1 was next week we’ll learn how to train the neural network!
Guess you were talking about the lab that demonstrates how Tensorflow model resembles our Course one linear model? I remember, in that lab, we assign trained parameter values to them and compare their outputs.