Automatically discovering image categories in unlabeled natural images is one of the important goals of unsupervised learning. However, the task is challenging and even human beings define visual categories based on a large amount of prior knowledge. In this paper, we similarly utilize prior knowledge to facilitate the discovery of image categories. We present a novel end-to-end network to map ...

One large problem when employing a similarity function to measure the similarities between new and prior cases is to determine the weights of the features. This paper proposes a new method of learning weights using a genetic algorithm based on the similarity information of given examples. This method is suitable for both linear and nonlinear similarity functions. Our experimental results show t...

How much did a network change since yesterday? How different is the wiring between Bob’s brain (a left-handed male) and Alice’s brain (a right-handed female), and how is it different? Graph similarity with given node correspondence, i.e. the detection of changes in the connectivity of graphs, arises in numerous settings. In this work, we formally state the axioms and desired properties of the g...

A strategy for automatic test case selection based on the use of a similarity function is presented. Test case selection is a crucial activity to model-based testing since the number of automatically generated test cases is usually enormous and possibly unfeasible. Also, a considerable number of test cases are redundant, that is, they exercise similar features of the application and/or are capa...

Graph partitioning, or network clustering, is an essential research problem in many areas. Current approaches, however, have difficulty splitting two clusters that are densely connected by one or more “hub” vertices. Further, traditional methods are less able to deal with very confused structures. In this paper we propose a novel similarity-based definition of the quality of a partitioning of a...

Genomic centers discover increasingly many protein sequences and structures, but not necessarily their full biological functions. Thus, currently, less than one percent of proteins have experimentally verified biochemical activities. To fill this gap, function prediction algorithms apply metrics of similarity between proteins on the premise that those sufficiently alike in sequence, or structur...

Investigation of biological processes using selective chemical interventions is generally applied in biomedical research and drug discovery. Many studies of this kind make use of gene expression experiments to explore cellular responses to chemical interventions. Recently, some research groups constructed libraries of chemical related expression profiles, and introduced similarity comparison in...

The article mainly studies the contracting similarity fixed point and the structure of the general Sierpinski gasket. Firstly, the paper analyzes the importance of contracting similarity fixed point in fractal geometry. Based on a series of definitions, the article studies the contracting similarity fixed point. Then, the paper researches on the structure of the general Sierpinski gasket, and d...

The AAA+ (ATPases associated with various cellular activities) superfamily of proteins represents a distinct lineage of the larger class of P-loop NTPases. Members of this superfamily use the power of nucleotide binding and hydrolysis to direct molecular remodelling events. All AAA+ proteins share a common core architecture, which, through various sequence and structural modifications, has been...

This article presents new alternatives to the similarity function for the TextRank algorithm for automated summarization of texts. We describe the generalities of the algorithm and the different functions we propose. Some of these variants achieve a significative improvement using the same metrics and dataset as the original publication.