The effect of the choice of neural network depth and breadth on the size of its hypothesis space
Szymanski, Lech, McCane, Brendan, Albert, Michael
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 $l$.
Jun-6-2018
Technology: Information Technology > Artificial Intelligence > Machine Learning > Neural Networks > Deep Learning (0.47)