arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.00732cond-mat.dis-nnmath.PRstat.ML
收藏

具有稀疏连通性的单层人工神经网络的渐近性质

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

Christian Hirsch, Matthias Neumann, Volker Schmidt

摘要:

在神经元数目和随机梯度下降的训练迭代次数同时增加的情况下,导出了具有稀疏连通性的单层人工神经网络参数经验分布的大数定律.

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑