Convolutional Conditional Neural Processes
Convolutional Conditional Neural Processes
复制标题
DOI：
10.17863/cam.48067
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Jonathan Gordon;W. Bruinsma;Andrew Y. K. Foong;James Requeima;Yann Dubois;Richard E. Turner
中科院分区：
文献类型：
--
作者：
Jonathan Gordon;W. Bruinsma;Andrew Y. K. Foong;James Requeima;Yann Dubois;Richard E. Turner
我们介绍卷积条件神经过程（ConvCNP），这是神经过程家族的新成员，它对数据中的平移等方差进行建模。平移等方差是许多学习问题的重要归纳偏差，包括时间序列建模，空间数据和图像。该模型将数据集嵌入到无限维函数空间中，而不是有限维向量空间。为了形式化这一概念，我们扩展了集合的神经表示理论，以包括函数表示，并证明任何反等变嵌入都可以使用卷积深集表示。我们在几种环境中评估了ConvCNP，证明与现有的NP相比，它们实现了最先进的性能。我们证明，在翻译等方差的建设，使零杆泛化具有挑战性的，域外的任务。
We introduce the Convolutional Conditional Neural Process (ConvCNP), a new member of the Neural Process family that models translation equivariance in the data. Translation equivariance is an important inductive bias for many learning problems including time series modelling, spatial data, and images. The model embeds data sets into an infinite-dimensional function space as opposed to a finite-dimensional vector space. To formalize this notion, we extend the theory of neural representations of sets to include functional representations, and demonstrate that any translation-equivariant embedding can be represented using a convolutional deep set. We evaluate ConvCNPs in several settings, demonstrating that they achieve state-of-the-art performance compared to existing NPs. We demonstrate that building in translation equivariance enables zero-shot generalization to challenging, out-of-domain tasks.