Designing a suitable image representation is one of the most fundamental issues of computer vision. There are three steps in the popular Bag of Words based image representation: feature extraction, coding and pooling. In the final step, current methods make an M × K encoded feature matrix degraded to a K-dimensional vector (histogram), where M is the number of features, and K is the size of the...

Image classification has become highly significant in the field of computer vision due to its wide array applications. In recent years, Convolutional Neural Networks (CNN) have emerged as potent tools for addressing this task. Attention mechanisms offer an effective approach enhance accuracy image classification. Despite Global Average Pooling (GAP) being a crucial component traditional attenti...

A new approach to drug discovery is based on the generation of high diversity libraries of DNA, RNA, peptides or small molecules. Search of such libraries for useful molecules is an optimization problem on high-dimensional molecular fitness landscapes. We utilize a spin-glass-like model, the NK model, to analyze search strategies based on pooling, mutation, recombination and selective hill-clim...

Genome-wide association scans for disease susceptibility genes of complex diseases require genotyping on a massive scale. A DNA pooling strategy for family-based association studies is described, which is robust to population stratification biases and to errors in pooling. It can achieve a statistical efficiency of 0.95 with approximately 1 of 8 or fewer genotyping efforts, and an efficiency of...

We investigate what computational mechanisms give rise to the nonlinearity of complex cell responses in the primary visual cortex. Complex cells are characterized by their nonlinear spatial properties such as spatial phase invariance and nonlinear spatial additivity. We carried out network simulations to estimate the second-order Wiener-like kernels for several different models. Models with non...