arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.19987cs.LGcs.CR
收藏

残差随机神经网络

Residual Random Neural Networks

Unlimited Analytics Inc.(无限分析公司)

M. Andrecut

AI总结:

本文打破随机权重单层前馈神经网络需大量隐藏神经元的传统假设,提出迭代残差训练方法并扩展至核版本,还给出可保护数据与模型的加密方法。

摘要:

具有随机权重的单层前馈神经网络是神经网络文献中反复出现的研究主题。这类网络的优势在于训练过程简化,可归结为求解岭回归问题。学界普遍假设,为获得良好的分类准确率,这类网络需要的隐藏神经元数量远多于数据样本的维度。与这一假设相反,本文证明当数据样本维度足够高时,即使隐藏神经元数量与数据样本维度处于同一数量级,也能取得良好的分类效果。受该结果启发,我们还为此类随机神经网络开发了一种高效的迭代残差训练方法,并将该算法扩展到神经网络模型的最小二乘核版本。此外,我们还提出了一种加密(混淆)方法,可同时保护数据和最终得到的网络模型。

英文摘要:

The single-layer feedforward neural network with random weights is a recurring motif in the neural networks literature. The advantage of these networks is their simplified training, which reduces to solving a ridge-regression problem. A general assumption is that these networks require a large number of hidden neurons relative to the dimensionality of the data samples, in order to achieve good classification accuracy. Contrary to this assumption, here we show that one can obtain good classification results even if the number of hidden neurons has the same order of magnitude as the dimensionality of the data samples, if this dimensionality is reasonably high. Inspired by this result, we also develop an efficient iterative residual training method for such random neural networks, and we extend the algorithm to the least-squares kernel version of the neural network model. Moreover, we also describe an encryption (obfuscation) method which can be used to protect both the data and the resulted network model.

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。

↑