Machine learning under resource constraints Fundamentals / / edited by Katharina Morik and Peter Marwedel

• Record Nr.: UNISA996503570003316
• Pubbl/distr/stampa: Berlin ; ; Boston : , : De Gruyter, , [2023]; ©2023
• ISBN: 3-11-078594-3
• Edizione: [1st ed.]
• Descrizione fisica: 1 online resource (xiii, 491 pages) : illustrations (chiefly colour)
• Collana: De Gruyter STEM ; ; Volume 1/3
• Disciplina: 006.31
• Soggetti: Machine learning; SCIENCE / Chemistry / General
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: "Part of the multi-volume work Machine Learning under Resource Constraints. In the series De Gruyter STEM."--Provided by publisher.; "Final report of CRC 876".; "Also of interest: Volume 2, Machine Learning under Resource Constraints. Discovery in Physics, Morik, Rhode (Eds.), 2023, ISBN 978-3-11-078595-1, e-ISBN 978-3-11-078596-8 ; Volume 3, Machine Learning under Resource Constraints. Applications, Morik, Rahnenführer, Wietfeld (Eds.), 2023, ISBN 978-3-11-078597-5, e-ISBN 978-3-11-078598-2."--Page ii.
• Nota di bibliografia: Includes bibliographical references (pages 437-483) and index.
• Nota di contenuto: 1 Introduction / Katharina Morik, Jian-Jia Chen -- ; 1.1 Embedded Systems and Sustainability -- ; 1.2 The Energy Consumption of Machine Learning -- ; 1.3 Memory Demands of Machine Learning -- ; 1.4 Structure of this Book -- ; 2 Data Gathering and Resource Measuring -- ; 2.1 Declarative Stream-Based Acquisition and Processing of OS Data with kCQL / Christoph Borchert, Jochen Streicher, Alexander Lochmann,Olaf Spinczyk -- ; 2.2 PhyNetLab Test Bed / Mojtaba Masoudinejad, Markus Buschhoff -- ; 2.3 Zero-Power/Low-Power Sensing / Andres Gomez, Lars Suter, Simon Mayer -- ; 3 Streaming Data, Small Devices -- ; 3.1 Summary Extraction from Streams / Sebastian Buschjäger, Katharina Morik -- ; 3.2 Coresets and Sketches for Regression Problems on Data Streams and Distributed Data / Alexander Munteanu -- ; 4 Structured Data -- ; 4.1 Spatio-Temporal Random Fields / Nico Piatkowski, Katharina Morik -- ; 4.2 ; The Weisfeiler-Leman Method for Machine Learning with Graphs / Nils Kriege, Christopher Morris -- ; 4.3 Deep Graph Representation Learning / Matthias Fey, Frank Weichert -- ; 4.4 High-Quality Parallel Max-Cut Approximation Algorithms for Shared Memory / Nico Bertram, Jonas Ellert, Johannes Fischer -- ; 4.5 Millions of Formulas / Lukas Pfahler -- ; 5 Cluster Analysis -- ; 5.1 Sparse Partitioning Around Medoids / Lars Lenssen, Erich Schubert -- ; 5.2 Clustering of Polygonal Curves and Time Series / Amer Krivošija -- ; 5.3 Data Aggregation for Hierarchical Clustering / Erich Schubert, Andreas Lang -- ; 5.4 Matrix Factorization with Binary Constraints / Sibylle Hess ; 6 Hardware-Aware Execution -- ; 6.1 FPGA-Based Backpropagation Engine for Feed-Forward Neural Networks / Wayne Luk, Ce Guo -- ; 6.2 Processor-Specific Code Transformation / Henning Funke, Jens Teubner -- ; 6.3 Extreme Multicore Classification / Erik Schultheis, Rohit Babbar -- ; 6.4 Optimization of ML on Modern Multicore Systems / Helena Kotthaus, Peter Marwedel -- 7 Memory Awareness -- ; 7.1 Efficient Memory Footprint Reduction / Helena Kotthaus, Peter Marwedel -- ; 7.2 Machine Learning Based on Emerging Memories / Mikail Yayla, Sebastian Buschjäger, Hussam Amrouch -- ; 7.3 Cache-Friendly Execution of Tree Ensembles / Sebastian Buschjäger, Kuan-Hsun Chen -- ; 8 Communication Awareness -- ; 8.1 Timing-Predictable Learning and Multiprocessor Synchronization / Kuan-Hsun Chen, Junjie Shi -- ; 8.2 Communication Architecture for Heterogeneous Hardware / Henning Funke, Jens Teubner -- ; 9 Energy Awareness -- ; 9.1 Integer Exponential Families / Nico Piatkowski -- ; 9.2 Power Consumption Analysis and Uplink Transmission Power / Robert Falkenberg.
• Sommario/riassunto: "Machine Learning under Resource Constraints addresses novel machine learning algorithms that are challenged by high-throughput data, by high dimensions, or by complex structures of the data in three volumes. Resource constraints are given by the relation between the demands for processing the data and the capacity of the computing machinery. The resources are runtime, memory, communication, and energy. Hence, modern computer architectures play a significant role. Novel machine learning algorithms are optimized with regard to minimal resource consumption. Moreover, learned predictions are executed on diverse architectures to save resources. It provides a comprehensive overview of the novel approaches to machine learning research that consider resource constraints, as well as the application of the described methods in various domains of science and engineering. Volume 1 establishes the foundations of this new field. It goes through all the steps from data collection, their summary and clustering, to the different aspects of resource-aware learning, i.e., hardware, memory, energy, and communication awareness. Several machine learning methods are inspected with respect to their resource requirements and how to enhance their scalability on diverse computing architectures ranging from embedded systems to large computing clusters. Ranges from embedded systems to large computing clusters. Provides application of the methods in various domains of science and engineering."--Provided by publisher.