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 2207.08896cs.LGstat.ML
收藏

关于多项式神经网络样本复杂性的研究

On the Study of Sample Complexity for Polynomial Neural Networks

UIUC(伊利诺伊大学厄巴纳-香槟分校)

Chao Pan, Chuanyi Zhang

摘要:

人工神经网络作为一种通用的机器学习方法,已经在许多模式识别和数据分析任务中建立了最先进的基准。在各种类型的神经网络结构中,多项式神经网络(PNN)最近被证明是可通过经由神经切线核的谱分析来分析的,并且在图像生成和人脸识别方面特别有效。然而,获得理论洞察PNN的计算和样本的复杂性仍然是一个悬而未决的问题。在本文中,我们在以往文献中的分析扩展到PNN,并获得新的结果的样本复杂性的PNN,这提供了一些见解,解释的泛化能力的PNN。

英文摘要:

As a general type of machine learning approach, artificial neural networks have established state-of-art benchmarks in many pattern recognition and data analysis tasks. Among various kinds of neural networks architectures, polynomial neural networks (PNNs) have been recently shown to be analyzable by spectrum analysis via neural tangent kernel, and particularly effective at image generation and face recognition. However, acquiring theoretical insight into the computation and sample complexity of PNNs remains an open problem. In this paper, we extend the analysis in previous literature to PNNs and obtain novel results on sample complexity of PNNs, which provides some insights in explaining the generalization ability of PNNs.

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。

↑