10444nam 22012135 450 99650357000331620231206231930.03-11-078594-310.1515/9783110785944(OCoLC)1356994849(MiAaPQ)EBC7156125(Au-PeEL)EBL7156125(OCoLC)1357015184(CKB)5580000000492226(EXLCZ)99558000000049222620230103h20232023 fy 0engurcn#|||mna|atxtrdacontentstirdacontentcrdamediacrrdacarrierMachine learning under resource constraintsFundamentals /edited by Katharina Morik and Peter Marwedel1st ed.Berlin ;Boston :De Gruyter,[2023]©20231 online resource (xiii, 491 pages) illustrations (chiefly colour)De Gruyter STEM ;Volume 1/3"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.3-11-078593-5 Includes bibliographical references (pages 437-483) and index.1Introduction /Katharina Morik, Jian-Jia Chen --1.1Embedded Systems and Sustainability --1.2The Energy Consumption of Machine Learning --1.3Memory Demands of Machine Learning --1.4Structure of this Book --2Data Gathering and Resource Measuring --2.1Declarative Stream-Based Acquisition and Processing of OS Data with kCQL /Christoph Borchert, Jochen Streicher, Alexander Lochmann,Olaf Spinczyk --2.2PhyNetLab Test Bed /Mojtaba Masoudinejad, Markus Buschhoff --2.3Zero-Power/Low-Power Sensing /Andres Gomez, Lars Suter, Simon Mayer --3 Streaming Data, Small Devices --3.1Summary Extraction from Streams /Sebastian Buschjäger, Katharina Morik --3.2Coresets and Sketches for Regression Problems on Data Streams and Distributed Data /Alexander Munteanu --4Structured Data --4.1Spatio-Temporal Random Fields /Nico Piatkowski, Katharina Morik --4.2The Weisfeiler-Leman Method for Machine Learning with Graphs /Nils Kriege, Christopher Morris --4.3Deep Graph Representation Learning /Matthias Fey, Frank Weichert --4.4High-Quality Parallel Max-Cut Approximation Algorithms for Shared Memory /Nico Bertram, Jonas Ellert, Johannes Fischer --4.5Millions of Formulas /Lukas Pfahler --5Cluster Analysis --5.1Sparse Partitioning Around Medoids /Lars Lenssen, Erich Schubert --5.2Clustering of Polygonal Curves and Time Series /Amer Krivošija --5.3Data Aggregation for Hierarchical Clustering /Erich Schubert, Andreas Lang --5.4Matrix Factorization with Binary Constraints /Sibylle Hess6Hardware-Aware Execution --6.1FPGA-Based Backpropagation Engine for Feed-Forward Neural Networks /Wayne Luk, Ce Guo --6.2Processor-Specific Code Transformation /Henning Funke, Jens Teubner --6.3Extreme Multicore Classification /Erik Schultheis, Rohit Babbar --6.4Optimization of ML on Modern Multicore Systems /Helena Kotthaus, Peter Marwedel --7 Memory Awareness --7.1Efficient Memory Footprint Reduction /Helena Kotthaus, Peter Marwedel --7.2Machine Learning Based on Emerging Memories /Mikail Yayla, Sebastian Buschjäger, Hussam Amrouch --7.3Cache-Friendly Execution of Tree Ensembles /Sebastian Buschjäger, Kuan-Hsun Chen --8Communication Awareness --8.1Timing-Predictable Learning and Multiprocessor Synchronization /Kuan-Hsun Chen, Junjie Shi --8.2Communication Architecture for Heterogeneous Hardware /Henning Funke, Jens Teubner --9Energy Awareness --9.1Integer Exponential Families /Nico Piatkowski --9.2Power Consumption Analysis and Uplink Transmission Power /Robert Falkenberg."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.De Gruyter STEM ;volume 1.Machine learningSCIENCE / Chemistry / GeneralbisacshArtificial Intelligence.Big Data and Machine Learning.Cyber-physical systems.Data mining for Ubiquitous System Software.Embedded Systems and Machine Learning.Highly Distributed Data.ML on Small devices.Machine learning for knowledge discovery.Machine learning in high-energy physics.Resource-Aware Machine Learning.Resource-Constrained Data Analysis.Machine learning.SCIENCE / Chemistry / General.006.31Amrouch Hussamctbhttps://id.loc.gov/vocabulary/relators/ctbBabbar Rohit1982-ctbhttps://id.loc.gov/vocabulary/relators/ctbBertram Nicoctbhttps://id.loc.gov/vocabulary/relators/ctbBorchert Christoph1984-ctbhttps://id.loc.gov/vocabulary/relators/ctbBuschhoff Markus1974-ctbhttps://id.loc.gov/vocabulary/relators/ctbBuschjäger Sebastian1990-ctbhttps://id.loc.gov/vocabulary/relators/ctbChen Jian-Jiactbhttps://id.loc.gov/vocabulary/relators/ctbChen Kuan-Hsun1989-ctbhttps://id.loc.gov/vocabulary/relators/ctbEllert Jonasctbhttps://id.loc.gov/vocabulary/relators/ctbFalkenberg Robertctbhttps://id.loc.gov/vocabulary/relators/ctbFey Matthias1990-ctbhttps://id.loc.gov/vocabulary/relators/ctbFischer Johannesctbhttps://id.loc.gov/vocabulary/relators/ctbFunke Henning1988-ctbhttps://id.loc.gov/vocabulary/relators/ctbGomez Andres1986-ctbhttps://id.loc.gov/vocabulary/relators/ctbGuo Cectbhttps://id.loc.gov/vocabulary/relators/ctbHeß Sibylle‏1984-ctbhttps://id.loc.gov/vocabulary/relators/ctbKotthaus Helena1984-ctbhttps://id.loc.gov/vocabulary/relators/ctbKriege Nils Morten1983-ctbhttps://id.loc.gov/vocabulary/relators/ctbKrivošija Amer1980-ctbhttps://id.loc.gov/vocabulary/relators/ctbLang Andreasctbhttps://id.loc.gov/vocabulary/relators/ctbLenssen Larsctbhttps://id.loc.gov/vocabulary/relators/ctbLochmann Alexander1988-ctbhttps://id.loc.gov/vocabulary/relators/ctbLuk Waynectbhttps://id.loc.gov/vocabulary/relators/ctbMarwedel Peterctbhttps://id.loc.gov/vocabulary/relators/ctbMarwedel Peteredthttp://id.loc.gov/vocabulary/relators/edtMasoudinejad Mojtaba1984-ctbhttps://id.loc.gov/vocabulary/relators/ctbMayer Simonctbhttps://id.loc.gov/vocabulary/relators/ctbMorik Katharinactbhttps://id.loc.gov/vocabulary/relators/ctbMorik Katharinaedthttp://id.loc.gov/vocabulary/relators/edtMorris Christopherctbhttps://id.loc.gov/vocabulary/relators/ctbMunteanu Alexanderctbhttps://id.loc.gov/vocabulary/relators/ctbPfahler Lukas1991-ctbhttps://id.loc.gov/vocabulary/relators/ctbPiatkowski Nicoctbhttps://id.loc.gov/vocabulary/relators/ctbSchubert Erichctbhttps://id.loc.gov/vocabulary/relators/ctbSchultheis Erikctbhttps://id.loc.gov/vocabulary/relators/ctbShi Junjiectbhttps://id.loc.gov/vocabulary/relators/ctbSpinczyk Olaf1970-ctbhttps://id.loc.gov/vocabulary/relators/ctbStreicher Jochenctbhttps://id.loc.gov/vocabulary/relators/ctbSuter Larsctbhttps://id.loc.gov/vocabulary/relators/ctbTeubner Jens(Jens Thilo)‏ctbhttps://id.loc.gov/vocabulary/relators/ctbWeichert Frankctbhttps://id.loc.gov/vocabulary/relators/ctbYayla Mikailctbhttps://id.loc.gov/vocabulary/relators/ctbHUAHUAUMCDLCDE-B1597CaOWtUBOOK996503570003316Machine Learning under Resource Constraints3011774UNISA