# Can a second network take as input the weights of a first network and help training the first network?

I understand that as a network learns about an output with regards to an input, weights are updated according to how wrong the guess was for that node. So, over time, the weights move in the "direction" towards the correct value.

Is it possible to use a separate neural network that takes as input the weights of the first network while it trains to try approximating that "direction" and, in effect, pushing the weights in that direction faster?