Convolutional neural network (CNN) architectures utilize downsampling layers, which restrict the subsequent layers to learn spatially invariant features while reducing computational costs. However, such a downsampling operation makes it impossible to use the full spectrum of input features. Motivated by this observation, we propose a novel layer called parallel grid pooling (PGP) which is appli...

Over 15% of the data sets catalogued in the Gene Expression Omnibus Database involve RNA samples that have been pooled before hybridization. Pooling affects data quality and inference, but the exact effects are not yet known because pooling has not been systematically studied in the context of microarray experiments. Here we report on the results of an experiment designed to evaluate the utilit...

The screening of data sets for "positive data objects" is essential to modern technology. A (group) test that indicates whether a positive data object is in a specific subset or pool of the dataset can greatly facilitate the identification of all the positive data objects. A collection of tested pools is called a pooling design. Pooling designs are standard experimental tools in many biotechnic...

A key step in many image quantification solutions is feature pooling, where subsets of lower-level features are combined so that higher-level, more invariant predictions can be made. The pooling region which defines the subsets often has a fixed spatial size and geometry, but data adaptive pooling regions have also been used. In this paper we investigate pooling strategies for the data adaptive...

When using likelihood methods to quantify and to assess pooled data sets – thus assuming independence of dyads (S8 Text) – we explicitly allow m to vary across replicates while estimating a single RCP value in the likelihood-maximization process. When using bootstrap methods (S7 Text), as we do whenever individual-molecule data are available, we do not explicitly account for the possibility tha...

We describe several experiments that were conducted to assess the viability of data pooling as a means to improve speech-recognition performance for under-resourced languages. Two groups of closely related languages from the Southern Bantu language family were studied, and our tests involved phoneme recognition on telephone speech using standard tied-triphone Hidden Markov Models. Approximately...

BACKGROUND Data confidentiality and shared use of research data are two desirable but sometimes conflicting goals in research with multi-center studies and distributed data. While ideal for straightforward analysis, confidentiality restrictions forbid creation of a single dataset that includes covariate information of all participants. Current approaches such as aggregate data sharing, distribu...