Squeeze-and-Excitation Networks
The central building block of convolutional neural networks (CNNs) is the convolution operator, which enables networks to construct informative features by fusing both spatial a...
Publications
Explore 1,426 academic publications
Showing 12 of
1,426 publications
Linear Models and Empirical Bayes Methods for Assessing Differential Expression in Microarray Experiments
The problem of identifying differentially expressed genes in designed microarray experiments is considered. Lonnstedt and Speed (2002) derived an expression for the posterior od...
A Mathematical Theory of Evidence
Both in science and in practical affairs we reason by combining facts only inconclusively supported by evidence. Building on an abstract understanding of this process of combina...
Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring
Although cancer classification has improved over the past 30 years, there has been no general approach for identifying new cancer classes (class discovery) or for assigning tumo...
Photocatalysis on TiO2 Surfaces: Principles, Mechanisms, and Selected Results
ADVERTISEMENT RETURN TO ISSUEPREVArticleNEXTPhotocatalysis on TiO2 Surfaces: Principles, Mechanisms, and Selected ResultsAmy L. Linsebigler, Guangquan Lu, and John T. Yates Jr.C...
A survey on Image Data Augmentation for Deep Learning
Abstract Deep convolutional neural networks have performed remarkably well on many Computer Vision tasks. However, these networks are heavily reliant on big data to avoid overfi...
Fit indices in covariance structure modeling: Sensitivity to underparameterized model misspecification.
This study evaluated the sensitivity of maximum likelihood (ML)-, generalized least squares (GLS)-, and asymptotic distribution-free (ADF)-based fit indices to model misspecific...
Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications
The purpose of this study was to classify breast carcinomas based on variations in gene expression patterns derived from cDNA microarrays and to correlate tumor characteristics ...
Significance analysis of microarrays applied to the ionizing radiation response
Microarrays can measure the expression of thousands of genes to identify changes in expression between different biological states. Methods are needed to determine the significa...