Deep learning method for testing the cosmic distance duality relation*

Representational Distance Learning for Deep Neural Networks

Deep neural networks (DNNs) provide useful models of visual representational transformations. We present a method that enables a DNN (student) to learn from the internal representational spaces of a reference model (teacher), which could be another DNN or, in the future, a biological brain. Representational spaces of the student and the teacher are characterized by representational distance mat...

A method for testing the cosmic homogeneity with Shannon entropy

We propose a method for testing Cosmic homogeneity based on the Shannon entropy in Information theory and test the potentials and limitations of the method on Monte Carlo simulations of some homogeneous and inhomogeneous 3D point process in a finite region of space. We analyze a set of N-body simulations to investigate the prospect of determining the scale of homogeneity with the proposed metho...

Efficient Method Based on Combination of Deep Learning Models for Sentiment Analysis of Text

People's opinions about a specific concept are considered as one of the most important textual data that are available on the web. However, finding and monitoring web pages containing these comments and extracting valuable information from them is very difficult. In this regard, developing automatic sentiment analysis systems that can extract opinions and express their intellectual process has ...

A Method for Defuzzication by Weighted Distance

A Hybrid Method for Distance Metric Learning

We consider the problem of learning a measure of distance among vectors in a feature space and propose a hybrid method that simultaneously learns from similarity ratings assigned to pairs of vectors and class labels assigned to individual vectors. Our method is based on a generative model in which class labels can provide information that is not encoded in feature vectors but yet relates to per...