Existing few-shot learning approaches are based on either meta-learning or metriclearning, which would suffer if the tasks have varying numbers of classes and/or the tasks diverge significantly. We propose meta metric learning to deal with the limitations of the existing few-shot learning approaches. Our meta metric learning approach consists of two components, task-specific learners that explo...

This paper discusses the opportunities arising from the employment of meta-adaptivity as a tool that can facilitate the design of adaptation. The discussion is structured around a specific example problem in the domain of adaptive course delivery systems. The paper builds upon this example to argue that meta-adaptivity is a viable solution to the “ground up” design of adaptive systems, and may ...

Is the Innovation Society sustainable? We argue that the way in which our society organizes its innovation processes generates endogenous crises, and the ideology that sustains this organization makes it difficult to confront this meta-crisis economically or politically. We claim that the key to constructing a socially sustainable future is the mobilization of civil society, with respect to two...

Meta-Learning has been successfully applied to acquire knowledge used to support the selection of learning algorithms. Each training example in Meta-Learning (i.e. each meta-example) is related to a learning problem and stores the experience obtained in the empirical evaluation of a set of candidate algorithms when applied to the problem. The generation of a good set of meta-examples can be a c...

Region-based tests are becoming a popular tool for analyzing rare genetic variants. In order for these tests to have adequate power, it is often necessary to meta-analyze information from multiple contributing studies, where consent restrictions make it difficult or impossible to share individual level data. We present the R package seqMeta for meta-analyzing region based tests, such as SKAT, S...

Region-based tests are becoming a popular tool for analyzing rare genetic variants. In order for these tests to have adequate power, it is often necessary to meta-analyze information from multiple contributing studies, where consent restrictions make it difficult or impossible to share individual level data. We present the R package seqMeta for meta-analyzing region based tests, such as SKAT, S...

In this paper, we analyze the quality of several commercial tools for sentiment detection. All tools are tested on nearly 30,000 short texts from various sources, such as tweets, news, reviews etc. The best commercial tools have average accuracy of 60%. We then apply machine learning techniques (Random Forests) to combine all tools, and show that this results in a meta-classifier that improves ...

In the analysis by Brown and colleagues that compared the current rnammography reading policy at St. Margaret's Hospital (double reading with consensus required for recall) with 2 alternative hypothetical strategies, the authors showed that the current strategy used is the most cost-effective. 2 elements of this study must he considered when attempting to generalise the conclusions to other set...

1 Departamento de Engenharia de Produção, Universidade Federal de Sao Carlos, C.P. 676, 13565-905, Sao Carlos, SP, Brazil [email protected]; [email protected] 2 Departamento de Matemática, Estat́ıstica e Computação, Universidade Estadual Paulista, C.P. 1234, 19060-400, Presidente Prudente, SP, Brazil [email protected] 3 Dept. of Technology and Operations Management, Univers...