most citedThe empirical size of trained neural networks

3 citations · 3 across the 1 of their papers we have counts for

collaborators

1 paper

stat.ML2016★ 3 cited

The empirical size of trained neural networks

Kevin K. Chen, Anthony Gamst, Alden Walker

ReLU neural networks define piecewise linear functions of their inputs. However, initializing and training a neural network is very different from fitting a linear spline. In this…