The effect of the choice of neural network depth and breadth on the size of its hypothesis space

Szymanski, Lech, McCane, Brendan, Albert, Michael Machine Learning 

We show that the number of unique function mappings in a neural network hypothesis space is inversely proportional to $\prod_lU_l!$, where $U_{l}$ is the number of neurons in the hidden layer $l$.

Duplicate Docs Excel Report

None found

Similar Docs  Excel Report  more

None found