Entropy in Machine Learning Applications

ISBN 10: 3725830657 / ISBN 13: 9783725830657

Published by MDPI AG, 2025

About this Item

Entropy in Machine Learning Applications | Buch | Englisch | 2025 | MDPI AG | EAN 9783725830657 | Verantwortliche Person für die EU: Libri GmbH, Europaallee 1, 36244 Bad Hersfeld, gpsr[at]libri[dot]de | Anbieter: preigu Print on Demand.

Seller Inventory # 131669415

Bibliographic Details

• Title: Entropy in Machine Learning Applications
• Publisher: MDPI AG
• Publication Date: 2025
• Language: English
• ISBN 10: 3725830657
• ISBN 13: 9783725830657
• Binding: Buch
• Condition: Neu
• Dimensions: 250W x 175H x 20D millimeters 250 millimeters width by 175 millimeters height by 20 millimeters depth
• Weight: 810 grams
• Seller catalogs:
  • Bücher

About this title

Synopsis

The aim of this reprint is to inform readers of the latest developments in methods and applications of machine learning and deep learning in certain fields, including the following: a semantically enhanced social network user alignment algorithm to perform user alignment; a congestion control mechanism based on deep reinforcement learning; problem solving involving low-accuracy, large-entropy perturbation; information loss in the calculation process of fault feature parameters of rolling bearing; a hybrid recommendation model combining autoencoder and latent feature analysis techniques; extracting knowledge from published papers and reports on drilling to guide the control of wells; an improved binary golden jackal optimization algorithm; water quality prediction based on machine learning and comprehensive weighting methods; redundancy of crossentropy calculation in deep learning of classifiers; automatic vertebral rotation angle measurement of vertebrae using an improved transformer network; defining suitable graph contrastive learning through applications of graph information bottlenecks and structural entropy theories; and a comprehensive examination of the latest advancements in deep learning methodologies. We hope that the papers in this Special Issue can contribute to promoting and facilitating the further research and application of machine learning methods.