Asymptotic properties of one-layer artificial neural networks with sparse connectivity
arXiv:2112.00732v2
Originality Synthesis-oriented
AI Analysis
This provides theoretical insights into the behavior of sparse neural networks during training, which is incremental to existing asymptotic analysis.
The paper derived a law of large numbers for the empirical distribution of parameters in one-layer artificial neural networks with sparse connectivity, as the number of neurons and training iterations increase simultaneously.
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.