Results 21 to 30 of about 24,502 (300)

Reviewing Evolution of Learning Functions and Semantic Information Measures for Understanding Deep Learning

Entropy, 2023
A new trend in deep learning, represented by Mutual Information Neural Estimation (MINE) and Information Noise Contrast Estimation (InfoNCE), is emerging. In this trend, similarity functions and Estimated Mutual Information (EMI) are used as learning and
Chenguang Lu
doaj   +1 more source

Two Measures of Dependence

Entropy, 2019
Two families of dependence measures between random variables are introduced. They are based on the Rényi divergence of order α and the relative
Amos Lapidoth, Christoph Pfister
doaj   +1 more source

Modeling Categorical Variables by Mutual Information Decomposition

, 2023
This paper proposed the use of mutual information (MI) decomposition as a novel approach to identifying indispensable variables and their interactions for contingency table analysis.
Philip E. Cheng, Jiun-Wei Liou, Michelle Liou   +2 more
core   +1 more source

Self-MI: Efficient Multimodal Fusion via Self-Supervised Multi-Task Learning with Auxiliary Mutual Information Maximization

CoRR, 2023
Accepted at The 37th Pacific Asia Conference on Language, Information and Computation (PACLIC 37)
Cam-Van Nguyen Thi, Ngoc-Hoa Thi Nguyen, Duc-Trong Le, Quang-Thuy Ha   +3 more
openaire   +3 more sources

Prediction of performance of the DVB-SH system relying on mutual information [PDF]

, 2010
DVB-SH (Digital Video Broadcasting-Satellite Handled) is a broadcasting standard dedicated to hybrid broadcasting systems combining a satellite and a terrestrial part. On the satellite part, dedicated interleaving and time slicing mechanisms are proposed
Chauvet, Wilfried, Amiot-Bazile, Caroline, Lacan, Jérôme, Jerome Lacan, Caroline Amiot-Bazile, Wilfried Chauvet   +5 more
core   +1 more source

Registration of Brain MRI/PET Images Based on Adaptive Combination of Intensity and Gradient Field Mutual Information

International Journal of Biomedical Imaging, 2007
Traditional mutual information (MI) function aligns two multimodality images with intensity information, lacking spatial information, so that it usually presents many local maxima that can lead to inaccurate registration.
Jiangang Liu, Jie Tian
doaj   +1 more source

ClearF++: Improved Supervised Feature Scoring Using Feature Clustering in Class-Wise Embedding and Reconstruction

Bioengineering, 2023
Feature selection methods are essential for accurate disease classification and identifying informative biomarkers. While information-theoretic methods have been widely used, they often exhibit limitations such as high computational costs. Our previously
Sehee Wang, So Yeon Kim, Kyung-Ah Sohn
doaj   +1 more source

Comparison of co-expression measures: mutual information, correlation, and model based indices

BMC Bioinformatics, 2012
Background Co-expression measures are often used to define networks among genes. Mutual information (MI) is often used as a generalized correlation measure.
Song Lin, Langfelder Peter, Horvath Steve   +2 more
doaj   +1 more source

MI$$^2$$GAN: Generative Adversarial Network for Medical Image Domain Adaptation Using Mutual Information Constraint [PDF]

, 2020
The first two authors contributed ...
Xinpeng Xie, Jiawei Chen 0009, Yuexiang Li, Linlin Shen, Kai Ma 0002, Yefeng Zheng 0001   +5 more
openaire   +2 more sources

Achievable information rate optimization in C-band optical fiber communication system

Frontiers of Optoelectronics, 2023
Optical fiber communication networks play an important role in the global telecommunication network. However, nonlinear effects in the optical fiber and transceiver noise greatly limit the performance of fiber communication systems.
Zheng Liu, Tianhua Xu, Ji Qi, Joshua Uduagbomen, Jian Zhao, Tiegen Liu   +5 more
doaj   +1 more source