Reprint

Machine Learning for Pattern Recognition

Edited by
July 2024
200 pages
  • ISBN978-3-7258-1591-3 (Hardback)
  • ISBN978-3-7258-1592-0 (PDF)

Print copies available soon

This book is a reprint of the Special Issue Machine Learning for Pattern Recognition that was published in

Computer Science & Mathematics
Summary

In recently arisen digital age, machine learning technology has made huge significant progress, revolutionizing applications in fields such as image recognition, speech processing, and natural language processing. These technologies have not only changed our daily lives, but have also had a profound impact on medicine, finance, transportation and other fields. However, pattern recognition, as an important branch of machine learning, still faces many challenges and problems. This reprint brings together contributions from leading experts in their fields. Each paper provides valuable insights into the latest trends, methods, and challenges in state-of-the-art applications of machine learning for pattern recognition. In addition, the research in each paper not only showcases the latest advancements in machine learning algorithms but also discusses their successful applications and the challenges encountered in real-world scenarios. As editors, we are honored to present this reprint, and we hope that readers, whether they be researchers, engineers, and students, will find inspiration and guidance in these papers as they explore the growing field of machine learning for pattern recognition. We express our gratitude to the authors for their outstanding contributions, to the reviewers for their critical evaluation, and to the assistant editor Mr. Musea Wu for his enthusiastic help. We are also sincerely grateful to our readers, whose curiosity and enthusiasm continue to drive innovation in this exciting field.

Format
  • Hardback
License and Copyright
© 2018 MDPI; under CC BY-NC-ND license
Keywords
Kullback–Leibler divergence; α-divergences; comparable weighted means; weighted quasi-arithmetic means; information geometry; conformal divergences; k-means clustering; topological data analysis; machine learning; persistent homology; clustering; anomaly detection; morphotype; lip-reading; word recognition; deep neural network; LRW; OuluVS; CUAVE; SSSD; 3D convolutional layer; ResNet; WideResNet; EfficientNet; transformer; ViT; ViViT; MS-TCN; AIS; vessel classification; TOCAT; deep learning algorithm; tympanic membrane; Tensorflow; optical coherence tomography; convolutional neural network; machine learning; neural network; pattern recognition; meteor; fluorescence telescope; orbital experiment; UV illumination; atmosphere; deep learning; image object detection; internet of things; structural similarity index measure (SSIM); Parkinson’s disease; speech processing; pitch synchronous segmentation; MFCC; relational learning; dimensionality reduction; graph embedding; trace ratio; document understanding and recognition; face recognition; sodium dodecyl sulfate–polyacrylamide gel electrophoresis; image analysis; protein band; molecular weight; image segmentation; binary mask; deep learning; point cloud; attention mechanism; pattern recognition