Machine learning under resource constraints. Fundamentals /

"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.

Introduction /; Embedded Systems and Sustainability --; The Energy Consumption of Machine Learning --; Memory Demands of Machine Learning --; Structure of this Book --; Data Gathering and Resource Measuring --; Declarative Stream-Based Acquisition and Processing of OS Data with kCQL /; PhyNetLab Test Bed /; Zero-Power/Low-Power Sensing /; Summary Extraction from Streams /; Coresets and Sketches for Regression Problems on Data Streams and Distributed Data /; Structured Data --; Spatio-Temporal Random Fields /; The Weisfeiler-Leman Method for Machine Learning with Graphs /; Deep Graph Representation Learning /; High-Quality Parallel Max-Cut Approximation Algorithms for Shared Memory /; Millions of Formulas /; Cluster Analysis --; Sparse Partitioning Around Medoids /; Clustering of Polygonal Curves and Time Series /; Data Aggregation for Hierarchical Clustering /; Matrix Factorization with Binary Constraints /; Hardware-Aware Execution --; FPGA-Based Backpropagation Engine for Feed-Forward Neural Networks /; Processor-Specific Code Transformation /; Extreme Multicore Classification /; Optimization of ML on Modern Multicore Systems /; 7 Memory Awareness --; Efficient Memory Footprint Reduction /; Machine Learning Based on Emerging Memories /; Cache-Friendly Execution of Tree Ensembles /; Communication Awareness --; Timing-Predictable Learning and Multiprocessor Synchronization /; Communication Architecture for Heterogeneous Hardware /; Energy Awareness --; Integer Exponential Families /; Power Consumption Analysis and Uplink Transmission Power / / Katharina Morik, Jian-Jia Chen --; Christoph Borchert, Jochen Streicher, Alexander Lochmann,Olaf Spinczyk --; Mojtaba Masoudinejad, Markus Buschhoff --; Andres Gomez, Lars Suter, Simon Mayer --; Sebastian Buschjäger, Katharina Morik --; Alexander Munteanu --; Nico Piatkowski, Katharina Morik --; Nils Kriege, Christopher Morris --; Matthias Fey, Frank Weichert --; Nico Bertram, Jonas Ellert, Johannes Fischer --; Lukas Pfahler --; Lars Lenssen, Erich Schubert --; Amer Krivošija --; Erich Schubert, Andreas Lang --; Sibylle Hess; Wayne Luk, Ce Guo --; Henning Funke, Jens Teubner --; Erik Schultheis, Rohit Babbar --; Helena Kotthaus, Peter Marwedel --; Helena Kotthaus, Peter Marwedel --; Mikail Yayla, Sebastian Buschjäger, Hussam Amrouch --; Sebastian Buschjäger, Kuan-Hsun Chen --; Kuan-Hsun Chen, Junjie Shi --; Henning Funke, Jens Teubner --; Nico Piatkowski --; Robert Falkenberg.