arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.10351cs.LGmath.PRstat.ML
收藏

Dropout神经网络的通用逼近

Universal Approximation in Dropout Neural Networks

Eindhoven University of Technology(埃因霍温理工大学)

Oxana A. Manita, Mark A. Peletier, Jacobus W. Portegies, Jaron Sanders, Albert Senen-Cerda

摘要:

我们证明了两个普遍的逼近定理的范围dropout神经网络。这些是前馈神经网络,其中每个边缘被赋予一个随机$\{0,1\}$值滤波器,具有两种操作模式:在第一种模式中,每个边缘输出乘以其随机滤波器,从而产生随机输出,而在第二种模式中,每个边缘输出乘以其滤波器的期望,从而产生确定性输出。通常在训练期间使用随机模式,而在测试和预测期间使用确定性模式。这两个定理都有以下形式:给定一个函数来近似和一个阈值$\varepsilon>0$,存在一个丢弃网络,它在概率上和在$L^q$中是$\varepsilon$ -接近的。第一个定理适用于随机模式下的丢弃网络。它对激活函数的假设很少,适用于广泛的网络类别,甚至可以应用于神经网络以外的近似方案。核心是一种代数性质,表明确定性网络可以与随机网络在预期中完全匹配。第二个定理提出了更强有力的假设,并给出了更强有力的结果。给定一个函数来近似,它提供了一个同时在两种模式下近似的网络的存在。证明组件是由独立副本递归替换边,以及将所得较大网络耦合到输入的特殊第一层替换。被近似的函数被假定为一般赋范空间的元素,并且近似在相应的范数中被度量。网络是明确构建的。由于证明方法的不同,这两个结果对随机丢弃网络的逼近性质给出了独立的见解。由此,我们建立了dropout神经网络广泛地满足普适逼近性质。

英文摘要:

We prove two universal approximation theorems for a range of dropout neural networks. These are feed-forward neural networks in which each edge is given a random $\{0,1\}$-valued filter, that have two modes of operation: in the first each edge output is multiplied by its random filter, resulting in a random output, while in the second each edge output is multiplied by the expectation of its filter, leading to a deterministic output. It is common to use the random mode during training and the deterministic mode during testing and prediction. Both theorems are of the following form: Given a function to approximate and a threshold $\varepsilon>0$, there exists a dropout network that is $\varepsilon$-close in probability and in $L^q$. The first theorem applies to dropout networks in the random mode. It assumes little on the activation function, applies to a wide class of networks, and can even be applied to approximation schemes other than neural networks. The core is an algebraic property that shows that deterministic networks can be exactly matched in expectation by random networks. The second theorem makes stronger assumptions and gives a stronger result. Given a function to approximate, it provides existence of a network that approximates in both modes simultaneously. Proof components are a recursive replacement of edges by independent copies, and a special first-layer replacement that couples the resulting larger network to the input. The functions to be approximated are assumed to be elements of general normed spaces, and the approximations are measured in the corresponding norms. The networks are constructed explicitly. Because of the different methods of proof, the two results give independent insight into the approximation properties of random dropout networks. With this, we establish that dropout neural networks broadly satisfy a universal-approximation property.

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。

↑