A Case Study on Meta-Generalising: A Gaussian Processes Approach
A Case Study on Meta-Generalising: A Gaussian Processes Approach
复制标题
DOI：
10.5555/2503308.2188409
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
G. Skolidis;G. Sanguinetti
中科院分区：
文献类型：
--
作者：
G. Skolidis;G. Sanguinetti
我们提出了一个新的模型元泛化，即执行预测的基础上，从多个不同的，但相关的任务的信息的新任务。该模型是基于两个耦合高斯过程与结构化的协方差函数;一个模型通过学习一个约束的协方差函数封装的各种训练任务之间的关系进行预测，而第二个模型确定新任务的相似性，以前看到的任务。我们证明经验上的几个真实的和合成数据集的优势的方法和它的局限性，由于它的基础上的分布假设。
We propose a novel model for meta-generalisation, that is, performing prediction on novel tasks based on information from multiple different but related tasks. The model is based on two coupled Gaussian processes with structured covariance function; one model performs predictions by learning a constrained covariance function encapsulating the relations between the various training tasks, while the second model determines the similarity of new tasks to previously seen tasks. We demonstrate empirically on several real and synthetic data sets both the strengths of the approach and its limitations due to the distributional assumptions underpinning it.