Neutrosophic set is a part of neutrosophy which studies the origin, nature, and scope of neutralities, as well as their interactions with different ideational spectra. Neutrosophic set is a powerful general formal framework that has been recently proposed. However, neutrosophic set needs to be specified from a technical point of view. To this effect, we define the set-theoretic operators on an instance of neutrosophic set, we call it truth-value based interval neutrosophic set. We provide various properties of truth-value based interval neutrosophic sets, which are connected to the operations and relations over truth-value based interval neutrosophic sets.
The goal of text-to-image synthesis is to generate a visually realistic image that matches a given text description. In practice, the captions annotated by humans for the same image have large variance in terms of contents and the choice of words. The linguistic discrepancy between the captions of the identical image leads to the synthetic images deviating from the ground truth. To address this issue, we propose a contrastive learning approach to improve the quality and enhance the semantic consistency of synthetic images. In the pre-training stage, we utilize the contrastive learning approach to learn the consistent textual representations for the captions corresponding to the same image. Furthermore, in the following stage of GAN training, we employ the contrastive learning method to enhance the consistency between the generated images from the captions related to the same image. We evaluate our approach over two popular text-to-image synthesis models, AttnGAN and DM-GAN, on datasets CUB and COCO, respectively. Experimental results have shown that our approach can effectively improve the quality of synthetic images in terms of three metrics: IS, FID and R-precision. Especially, on the challenging COCO dataset, our approach boosts the FID significantly by 29.60% over AttnGAn and by 21.96% over DM-GAN.
This paper extends the relational model to represent indefinite and maybe kinds of incomplete information. A data structure, called an I-table, which is capable of representing indefinite and maybe facts, is introduced. The information content of I-tables is precisely defined, and an operator to remove redundant facts is presented. The relational algebra is then extended in a semantically correct way to operate on I-tables. Queries are posed in the same way as in conventional relational algebra; however, the user may now expect indefinite as well as maybe answers.
The basic unit of any nervous system is the neuron. Therefore, understanding the operation of nervous systems ultimately requires an inventory of their constituent neurons and synaptic connectivity, which form neural circuits. The presence of uniquely identifiable neurons or classes of neurons in many invertebrates has facilitated the construction of cellular-level connectivity diagrams that can be generalized across individuals within a species. Homologous neurons can also be recognized across species. Here we describe , a web-based tool that we are developing for cataloging, searching, and analyzing neuronal circuitry within and across species. Information from a single species is represented in an individual branch of NeuronBank. Users can search within a branch or perform queries across branches to look for similarities in neuronal circuits across species. The branches allow for an extensible ontology so that additional characteristics can be added as knowledge grows. Each entry in NeuronBank generates a unique accession ID, allowing it to be easily cited. There is also an automatic link to a Wiki page allowing an encyclopedic explanation of the entry. All of the 44 previously published neurons plus one previously unpublished neuron from the mollusc, Tritonia diomedea, have been entered into a branch of NeuronBank as have 4 previously published neurons from the mollusc, Melibe leonina. The ability to organize information about neuronal circuits will make this information more accessible, ultimately aiding research on these important models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.