We introduce the problem of zero-data learning, where a model must generalize to classes or tasks for which no training data are available and only a description of the classes or...
Matching Pursuit algorithms learn a function that is a weighted sum of basis functions, by sequentially appending functions to an initially empty basis, to approximate a target fu...
Background: Retinal photoreceptors are highly specialised cells, which detect light and are central to mammalian vision. Many retinal diseases occur as a result of inherited dysfu...
Haiying Wang, Huiru Zheng, David Simpson, Francisc...
It has been shown in prior work in management science, statistics and machine learning that using an ensemble of models often results in better performance than using a single ‘...
Abstract--We investigate parameter-based and distributionbased approaches to regularizing the generative, similarity-based classifier called local similarity discriminant analysis ...