Existing salient instance detection (SID) methods typically learn from pixel-level annotated datasets. In this paper, we present the first weakly-supervised approach to SID problem. Although weak supervision has been considered in general saliency detection, it is mainly based on using class labels for object localization. However, non-trivial use only instance-aware information, as instances w...

This research is a development that aims to produce learning innovations in the psychomotor domain for practice archival subjects. The design adapts Borg and Gall model which consists of eight stages, namely, (1) potential problems, (2) data collection, (3) product design, (4) validation, (5) revision, (6) products testing, (7) (8) mass production. was conducted at Office Administration Vocatio...

Autoencoders play a fundamental role in unsupervised learning and in deep architectures for transfer learning and other tasks. In spite of their fundamental role, only linear autoencoders over the real numbers have been solved analytically. Here we present a general mathematical framework for the study of both linear and non-linear autoencoders. The framework allows one to derive an analytical ...

(Supervised and Unsupervised STratified Adaptive IncrementalNetwork) is a network model of human category learning. SUSTAIN initially assumes a simple category structure. If simple solutions prove inadequate and SUSTAIN is confronted with a surprising event (e.g. it is told that a bat is a mammal instead of a bird), SUSTAIN recruits an additional cluster to represent the surprising event. Newly...

We discuss the detection of two Gaussian clusters given a cloud of points. The optimal learning curve for this unsupervised learning scenario is determined with a replica calculation. A comparison with principal component analysis and supervised learning allows to understand the three diierent learning phases observed.

We have investigated the developmental relationship of the hemopoietic and endothelial lineages in the floor of the chicken aorta, a site of hemopoietic progenitor emergence in the embryo proper. We show that, prior to the onset of hemopoiesis, the aortic endothelium uniformly expresses the endothelium-specific membrane receptor VEGF-R2. The onset of hemopoiesis can be determined by detecting t...

This article draws upon Diffusion of Innovations and Configurational theories to investigate how website features and email responses by 200 Swiss hotels reflect evolving Internet adoption. Complementary multivariate and artificial neural network (ANN) techniques support classifying the hotels into three clusters based on their website features. These clusters and the results of a structural eq...

We assess the possibility of determining the Hubble constant H0 by measuring time delays between multiple images of supernovae gravitationally lensed by rich clusters of galaxies and combining these delay measurements with detailed cluster-potential models based on other lensing constraints. Such a lensing determination of H0 would be complementary to those obtained from galaxyQSO lensing studi...

Research has shown that prolonged grief disorder (PGD) is a disorder distinct from other disorders including major depression and posttraumatic stress disorder (PTSD). This study aimed to extend this research by examining the distinctiveness of symptoms of PGD relative to symptoms of adult separation anxiety disorder, also taking into account depression. Data were available from 205 bereaved in...