Asymptotic properties of one-layer artificial neural networks with sparse connectivity

Hirsch, Christian, Neumann, Matthias, Schmidt, Volker

–arXiv.org Machine Learning 

A law of large numbers for the empirical distribution of parameters of a one-layer artificial neural networks with sparse connectivity is derived for a simultaneously increasing number of both, neurons and training iterations of the stochastic gradient descent.

arXiv.org Machine Learning

Dec-9-2021

arXiv.org    PDF

Add feedback