Information-Theoretic Methods in Deep Learning

The rapid development of deep learning has led to groundbreaking advancements across various fields, from computer vision to natural language processing and beyond. Information theory, as a mathematical foundation for understanding data representation, learning, and communication, has emerged as a p...

Olles dieđut

Furkejuvvon:
Bibliográfalaš dieđut
Materiálatiipa: Online
Giella:eaŋgalasgiella
Almmustuhtton: MDPI - Multidisciplinary Digital Publishing Institute 2025
Fáttát:
Liŋkkat:ONIX_20250220_9783725829828_514
Fáddágilkorat: Lasit fáddágilkoriid
Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!
_version_ 1869524854039904256
collection Directory of Open Access Books
description The rapid development of deep learning has led to groundbreaking advancements across various fields, from computer vision to natural language processing and beyond. Information theory, as a mathematical foundation for understanding data representation, learning, and communication, has emerged as a powerful tool in advancing deep learning methods.This Special Issue, "Information-Theoretic Methods in Deep Learning: Theory and Applications", presents cutting-edge research that bridges the gap between information theory and deep learning. It covers theoretical developments, innovative methodologies, and practical applications, offering new insights into the optimization, generalization, and interpretability of deep learning models. The collection includes contributions on: Theoretical frameworks combining information theory with deep learning architectures; Entropy-based and information bottleneck methods for model compression and generalization; Mutual information estimation for feature selection and representation learning; Applications of information-theoretic principles in natural language processing, computer vision, and neural network optimization.
format Online
id doab-20.500.12854ir-153150
institution Directory of Open Access Books
language eng
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher MDPI - Multidisciplinary Digital Publishing Institute
publisherStr MDPI - Multidisciplinary Digital Publishing Institute
record_format ojs
spelling doab-20.500.12854ir-1531502025-02-20T13:38:25Z Information-Theoretic Methods in Deep Learning Yang, Shuangming Yu, Shujian Sánchez Giraldo, Luis Gonzalo Chen, Badong sentiment analysis deep neural networks convolutional neural network ResNet Res2Net multiple time series forecasting method information bottleneck entropy KL-divergence mutual information deep models RNN U-Net partial convolutions information theory deep learning information plane kernels methods deep neural network generalization ability regularization method continual learning quadruped robot locomotion reinforcement learning plasticity active learning universal prediction deep active learning individual sequences normalized maximum likelihood out-of-distribution few-shot learning meta learning graph semi-supervision label propagation Gaussian kernel function D-S evidence theory self-supervised learning representation learning generative adversarial networks parameterized loss functions f-divergence Jensen-f-divergence time series modelling forecasting nonlinear modelling denoising anomaly detection degradation modelling machine learning thema EDItEUR::M Medicine and Nursing::MJ Clinical and internal medicine::MJC Diseases and disorders::MJCL Oncology thema EDItEUR::P Mathematics and Science The rapid development of deep learning has led to groundbreaking advancements across various fields, from computer vision to natural language processing and beyond. Information theory, as a mathematical foundation for understanding data representation, learning, and communication, has emerged as a powerful tool in advancing deep learning methods.This Special Issue, "Information-Theoretic Methods in Deep Learning: Theory and Applications", presents cutting-edge research that bridges the gap between information theory and deep learning. It covers theoretical developments, innovative methodologies, and practical applications, offering new insights into the optimization, generalization, and interpretability of deep learning models. The collection includes contributions on: Theoretical frameworks combining information theory with deep learning architectures; Entropy-based and information bottleneck methods for model compression and generalization; Mutual information estimation for feature selection and representation learning; Applications of information-theoretic principles in natural language processing, computer vision, and neural network optimization. 2025-02-20T13:38:22Z 2025-02-20T13:38:22Z 2025 book ONIX_20250220_9783725829828_514 9783725829828 9783725829811 https://directory.doabooks.org/handle/20.500.12854/153150 eng application/octet-stream Attribution 4.0 International https://mdpi.com/books/pdfview/book/10425 MDPI - Multidisciplinary Digital Publishing Institute 10.3390/books978-3-7258-2981-1 10.3390/books978-3-7258-2981-1 46cabcaa-dd94-4bfe-87b4-55023c1b36d0 9783725829828 9783725829811 244 Basel open access
spellingShingle sentiment analysis
deep neural networks
convolutional neural network
ResNet
Res2Net
multiple time series
forecasting method
information bottleneck
entropy
KL-divergence
mutual information
deep models
RNN
U-Net
partial convolutions
information theory
deep learning
information plane
kernels methods
deep neural network
generalization ability
regularization method
continual learning
quadruped robot locomotion
reinforcement learning
plasticity
active learning
universal prediction
deep active learning
individual sequences
normalized maximum likelihood
out-of-distribution
few-shot learning
meta learning
graph semi-supervision
label propagation
Gaussian kernel function
D-S evidence theory
self-supervised learning
representation learning
generative adversarial networks
parameterized loss functions
f-divergence
Jensen-f-divergence
time series modelling
forecasting
nonlinear modelling
denoising
anomaly detection
degradation modelling
machine learning
thema EDItEUR::M Medicine and Nursing::MJ Clinical and internal medicine::MJC Diseases and disorders::MJCL Oncology
thema EDItEUR::P Mathematics and Science
Information-Theoretic Methods in Deep Learning
title Information-Theoretic Methods in Deep Learning
title_full Information-Theoretic Methods in Deep Learning
title_fullStr Information-Theoretic Methods in Deep Learning
title_full_unstemmed Information-Theoretic Methods in Deep Learning
title_short Information-Theoretic Methods in Deep Learning
title_sort information theoretic methods in deep learning
topic sentiment analysis
deep neural networks
convolutional neural network
ResNet
Res2Net
multiple time series
forecasting method
information bottleneck
entropy
KL-divergence
mutual information
deep models
RNN
U-Net
partial convolutions
information theory
deep learning
information plane
kernels methods
deep neural network
generalization ability
regularization method
continual learning
quadruped robot locomotion
reinforcement learning
plasticity
active learning
universal prediction
deep active learning
individual sequences
normalized maximum likelihood
out-of-distribution
few-shot learning
meta learning
graph semi-supervision
label propagation
Gaussian kernel function
D-S evidence theory
self-supervised learning
representation learning
generative adversarial networks
parameterized loss functions
f-divergence
Jensen-f-divergence
time series modelling
forecasting
nonlinear modelling
denoising
anomaly detection
degradation modelling
machine learning
thema EDItEUR::M Medicine and Nursing::MJ Clinical and internal medicine::MJC Diseases and disorders::MJCL Oncology
thema EDItEUR::P Mathematics and Science
topic_facet sentiment analysis
deep neural networks
convolutional neural network
ResNet
Res2Net
multiple time series
forecasting method
information bottleneck
entropy
KL-divergence
mutual information
deep models
RNN
U-Net
partial convolutions
information theory
deep learning
information plane
kernels methods
deep neural network
generalization ability
regularization method
continual learning
quadruped robot locomotion
reinforcement learning
plasticity
active learning
universal prediction
deep active learning
individual sequences
normalized maximum likelihood
out-of-distribution
few-shot learning
meta learning
graph semi-supervision
label propagation
Gaussian kernel function
D-S evidence theory
self-supervised learning
representation learning
generative adversarial networks
parameterized loss functions
f-divergence
Jensen-f-divergence
time series modelling
forecasting
nonlinear modelling
denoising
anomaly detection
degradation modelling
machine learning
thema EDItEUR::M Medicine and Nursing::MJ Clinical and internal medicine::MJC Diseases and disorders::MJCL Oncology
thema EDItEUR::P Mathematics and Science
url ONIX_20250220_9783725829828_514