Machine Learning under Resource Constraints - Discovery in Physics

Machine Learning under Resource Constraints explores innovative machine learning algorithms that handle high-throughput data, high dimensions, or complex data structures. It emphasizes the optimization of resource consumption and the execution of learned predictions on diverse architectures. Volume 2 specifically focuses on machine learning in particle and astroparticle physics, where it processes vast amounts of data and contributes to knowledge discovery through encoded simulations and interpretation.

Format: Paperback / softback
Length: 363 pages
Publication date: 31 December 2022
Publisher: De Gruyter

Machine Learning under Resource Constraints delves into innovative machine learning algorithms that face the formidable challenges of handling high-throughput data,with high dimensions,or complex data structures across three comprehensive volumes. These challenges are inherently tied to the interplay between the demands placed on data processing and the capabilities of the computing machinery. The resources at hand include runtime,memory,communication,and energy,all of which play pivotal roles in modern computer architectures. Consequently, novel machine learning algorithms are meticulously engineered to optimize resource consumption,while also enabling the execution of learned predictions across diverse architectures to further conserve resources. This comprehensive work offers a thorough exploration of novel approaches to machine learning research that take into account resource constraints,as well as the practical applications of the described methods across various domains of science and engineering.

Volume 2 specifically focuses on the application of machine learning in the realm of knowledge discovery in particle and astroparticle physics. These instruments, such as particle detectors or telescopes, generate vast amounts of data, necessitating the use of machine learning not only for efficient data processing and the identification of relevant examples but also as an integral part of the knowledge discovery process itself. The physical knowledge underlying these phenomena is encoded in simulations, which serve as the training grounds for machine learning models. Simultaneously, the interpretation of these learned models expands our understanding of the physical world, fostering a cycle of theory enhancement supported by machine learning.

In summary, Machine Learning under Resource Constraints provides a comprehensive and in-depth exploration of the field, shedding light on the latest developments and methodologies that address the challenges posed by high-throughput data, high dimensions, and complex data structures. By examining the interplay between resource constraints and machine learning, this work offers valuable insights into the future of data analysis and knowledge discovery in diverse scientific and engineering domains.

Weight: 618g
Dimension: 240 x 170 (mm)
ISBN-13: 9783110785951