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 2203.02543math.FAstat.ML
收藏

脊、神经网络和Radon变换

Ridges, Neural Networks, and the Radon Transform

Michael Unser

摘要:

脊是由一维轮廓(激活)和多维方向向量表征的函数。脊在神经网络理论中作为神经元效应的功能描述符出现,其中方向向量被编码在线性权重中。在本文中,我们调查性质的Radon变换的脊和神经网络的表征。我们引入了一类广义的超球面Banach子空间(包括相关的子空间的措施),在其上的反投影算子是可逆的。给出了反投影算子可扩到全父空间且其零空间可识别为Banach补的条件。从第一原理开始,我们然后描述滤波Radon变换范围内的采样泛函。接下来,我们扩展脊的定义为任何分布的配置文件,并确定其(过滤)拉冬变换在充分的一般性。最后,我们应用我们的形式主义来澄清和简化文献中出现的关于ReLU网络最优性的一些结果和证明。

英文摘要:

A ridge is a function that is characterized by a one-dimensional profile (activation) and a multidimensional direction vector. Ridges appear in the theory of neural networks as functional descriptors of the effect of a neuron, with the direction vector being encoded in the linear weights. In this paper, we investigate properties of the Radon transform in relation to ridges and to the characterization of neural networks. We introduce a broad category of hyper-spherical Banach subspaces (including the relevant subspace of measures) over which the back-projection operator is invertible. We also give conditions under which the back-projection operator is extendable to the full parent space with its null space being identifiable as a Banach complement. Starting from first principles, we then characterize the sampling functionals that are in the range of the filtered Radon transform. Next, we extend the definition of ridges for any distributional profile and determine their (filtered) Radon transform in full generality. Finally, we apply our formalism to clarify and simplify some of the results and proofs on the optimality of ReLU networks that have appeared in the literature.

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。

↑