Bounded Turing Reductions and Data Processing Inequalities for Sequences
Sign Up to like & getrecommendations! Published in 2017 at "Theory of Computing Systems"
DOI: 10.1007/s00224-017-9804-7
Abstract: AbstractA data processing inequality states that the quantity of shared information between two entities (e.g. signals, strings) cannot be significantly increased when one of the entities is processed by certain kinds of transformations. In this… read more here.
Keywords: shared information; data processing; mdim; bounded turing ... See more keywords
Finite-Sample Analysis of Deep CCA-Based Unsupervised Post-Nonlinear Multimodal Learning.
Sign Up to like & getrecommendations! Published in 2022 at "IEEE transactions on neural networks and learning systems"
DOI: 10.1109/tnnls.2022.3160407
Abstract: Canonical correlation analysis (CCA) has been essential in unsupervised multimodal/multiview latent representation learning and data fusion. Classic CCA extracts shared information from multiple modalities of data using linear transformations. In recent years, deep neural networks-based… read more here.
Keywords: cca; multimodal; shared information; analysis ... See more keywords
On extractable shared information
Sign Up to like & getrecommendations! Published in 2017 at "Entropy"
DOI: 10.3390/e19070328
Abstract: We consider the problem of quantifying the information shared by a pair of random variables X 1 , X 2 about another variable S. We propose a new measure of shared information, called extractable shared… read more here.
Keywords: shared information; information; information shared; left monotonic ... See more keywords