Advances in Partitioning Techniques: A Prospective towards Artificial Intelligence

— —

Shankru Guggari Umadevi V

Advances in Partitioning Techniques

A Prospective towards Artificial Intelligence

Shankru Guggari, Umadevi V, Vijayakumar Kadappa

$336

Hardback

Forthcoming
Pre-Order now

QTY:

English

Chapman & Hall/CRC
02 June 2025

Probability & statistics; Algorithms & data structures; Data mining; Artificial intelligence

This book discusses various partitioning strategies tailored for traditional machine learning algorithms. It examines how data can be divided efficiently to enhance the performance and scalability of classic machine learning models. It explores how partitioning methods can be applied to neural networks and other deep learning architectures and describes various ways to accelerate training, reduce memory consumption, and enhance overall efficiency.

Graphs are prevalent in various AI domains. This book is specifically designed for graph data structures using partitioning techniques and also explores insights into optimizing graph algorithms and analytics. With the explosion of data, efficient partitioning becomes crucial for processing large datasets. This book discusses various partitioning techniques that enable effective management and analysis of big data, enhancing speed and resource utilization. Edge computing demands resource-efficient strategies. It examines partitioning methods tailored for edge devices, enabling AI capabilities at the edge while addressing resource. This book showcases how partitioning techniques have been successfully applied across various AI domains. It demonstrates real-world scenarios where partitioning optimizes AI algorithms and systems.

By bridging the gap between theory and practical applications, this book intends to equip researchers, practitioners, and students with invaluable insights into harnessing partitioning for optimizing AI-driven systems, data processing, and problem-solving strategies. It describes the various advantages and disadvantages of partitioning techniques. This book is a vital resource, illuminating the path towards unlocking the full potential of partitioning in shaping the future of AI technologies.

By: Shankru Guggari, Umadevi V, Vijayakumar Kadappa
Imprint: Chapman & Hall/CRC
Country of Publication: United Kingdom
Dimensions: Height: 234mm, Width: 156mm,
Weight: 410g
ISBN: 9781032750019
ISBN 10: 1032750014
Pages: 122
Publication Date: 02 June 2025
Audience: College/higher education , Professional and scholarly , Primary , Undergraduate
Format: Hardback
Publisher's Status: Forthcoming

Shankru Guggari is a machine learning specialist who primarily focuses on enhancing the performance of machine learning techniques. His research interests include pattern recognition, explainable AI, and machine learning. He has published his work in various international conferences and journals and has over four years of academic experience. Umadevi V, PhD from IIT Madras, is a Professor of Computer Science at BMS College of Engineering, Bangalore and a Senior IEEE member. She has published extensively in reputed journals and conferences and received grants for research in medical thermography. Vijaya Kumar Kadappa obtained his PhD in from the Central University of Hyderabad in 2010 and working as Professor at the Department of Computer Applications, BMS College of Engineering, Bangalore. He has 30+ research publications. Kadappa is a life member of IUPR-AI, ISTE, and CSI.