论文标题
Voronoi卷积神经网络
Voronoi Convolutional Neural Networks
论文作者
论文摘要
在这份技术报告中，我们研究了将卷积神经网络扩展到未以网格模式采样功能的设置。我们表明，通过将样品视为单元内函数的平均值，我们可以找到与CNN中使用的大多数层的自然等效物。我们还提出了一种使用标准凸几何算法准确地推断这些模型的算法。
In this technical report, we investigate extending convolutional neural networks to the setting where functions are not sampled in a grid pattern. We show that by treating the samples as the average of a function within a cell, we can find a natural equivalent of most layers used in CNN. We also present an algorithm for running inference for these models exactly using standard convex geometry algorithms.
