arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1910.11080cs.LGstat.ML
收藏

关于神经网络的样本复杂性

On sample complexity of neural networks

Universidade de Lisboa(里斯本大学);Centro de Matemática e Aplicações Fundamentais(基础数学与应用中心)

Alexander Usvyatsov

摘要:

我们认为由深度神经网络定义的函数是实数域的o-最小扩展中的可定义对象,并推导出此类网络的样本复杂度的几乎线性(在权重数量上)界。

英文摘要:

We consider functions defined by deep neural networks as definable objects in an o-miminal expansion of the real field, and derive an almost linear (in the number of weights) bound on sample complexity of such networks.

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。

↑