Katharina Morik - Böcker

This text provides information on learning robots. It treats this topic based on the idea that the integration of sensing and action is the central issue. In the first part of the book, aspects of learning in execution and control are discussed. Methods for the automatic synthesis of controllers, for active sensing, for learning to enhance assembly, and for learning sensor-based navigation are presented. Since robots are not isolated but should serve us, the second part of the book discusses learning for human-robot interaction. Methods of learning understandable concepts for assembly, monitoring, and navigation are described as well as optimizing the implementation of such understandable concepts for a robot's real-time performance. In terms of the study of embodied intelligence, the book asks how skills are acquired and where capabilities of execution and control come from. Can they be learned from examples or experience? What is the role of communication in the learning procedure? Whether we name it one way or the other, the methodological challenge is that of integrating learning capabilities into robots.

Making Robots Smarter is a book about learning robots. It treats this topic based on the idea that the integration of sensing and action is the central issue. In the first part of the book, aspects of learning in execution and control are discussed. Methods for the automatic synthesis of controllers, for active sensing, for learning to enhance assembly, and for learning sensor-based navigation are presented. Since robots are not isolated but should serve us, the second part of the book discusses learning for human-robot interaction. Methods of learning understandable concepts for assembly, monitoring, and navigation are described as well as optimizing the implementation of such understandable concepts for a robot's real-time performance. In terms of the study of embodied intelligence, Making Robots Smarter asks how skills are acquired and where capabilities of execution and control come from. Can they be learned from examples or experience? What is the role of communication in the learning procedure? Whether we name it one way or the other, the methodological challenge is that of integrating learning capabilities into robots.

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.

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 2 covers machine learning for knowledge discovery in particle and astroparticle physics. Their instruments, e.g., particle detectors or telescopes, gather petabytes of data. Here, machine learning is necessary not only to process the vast amounts of data and to detect the relevant examples efficiently, but also as part of the knowledge discovery process itself. The physical knowledge is encoded in simulations that are used to train the machine learning models. At the same time, the interpretation of the learned models serves to expand the physical knowledge. This results in a cycle of theory enhancement supported by machine learning.

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 3 describes how the resource-aware machine learning methods and techniques are used to successfully solve real-world problems. The book provides numerous specific application examples. In the areas of health and medicine, it is demonstrated how machine learning can improve risk modelling, diagnosis, and treatment selection for diseases. Machine learning supported quality control during the manufacturing process in a factory allows to reduce material and energy cost and save testing times is shown by the diverse real-time applications in electronics and steel production as well as milling. Additional application examples show, how machine-learning can make traffic, logistics and smart cities more effi cient and sustainable. Finally, mobile communications can benefi t substantially from machine learning, for example by uncovering hidden characteristics of the wireless channel.

Thiscovers topics such as renewable energy supply, energy storage and e-mobility, efficiencyin data centers and networks, sustainable food and water supply, sustainablehealth, industrial production and quality, etc.

Thiscovers topics such as renewable energy supply, energy storage and e-mobility, efficiencyin data centers and networks, sustainable food and water supply, sustainablehealth, industrial production and quality, etc.

Es wurde gezeigt, dass das Bootstrap-Problem bei der geometrischen Szenenrekonstruktion eine wichtige Rolle spielt und dass das Problem der physikalischen Korrespondenz als eine spezielle Sichtweise des Rekonstruktionsproblems gesehen werden kann. Weiterhin wurde ein wissensbasier- ter Ansatz vorgestellt, um das Bootstrap-Problem zu umgehen. Literatur Bajcsy + Lieberman 76 : Texture Gradient as a Depth Cue, R. Bajcsy und L.1. Lieberman, Computer Graphics and Image Processing 5, 52-67 (1976). Bartsch u.a. 86 : Merkmalsdetektion in Farbbildern als Grundlage zur Korrespondenzanalyse in Stereo-Bildfolgen, Thomas Bartsch, Leonie S. Dreschler-Fischer und Carsten Schroder, DAGM-86, pp. 94-97. Binford 81 : Inferring Surfaces /rom Images, Thomas O. Binford, Artificial Intelligence 17, 205-244 (1981) siehe auch: Brady 81, pp. 75-116. Blostein + Ahuja 87 : Representation and Three-Dimensional Interpretation of Image Texture: An Integrated Approach, Dorothea Blostein und Narendra Ahuja, ICCV-87, pp. 444-449. Brady 81 : Computer Vision, J.M. Brady (Rrsg.), North Holland Publ. Comp. Amsterdam 1981, reprinted /rom Artificial Intelligence 17 (1981).Clocksin 78 : Determining the Orientation of Surfaces /rom Optical Flow, W.F. Clocksin, Proc. AISB/GI-78 on Artificial Intelligence, Hamburg, July 18-20, 1978, pp. 73-102. Crowley 84a: A Computational Paradigm for Three Dimensional Scene Analysis, James 1. Crowley, Technical Report CMU-RI-TR-84-11 The Robotics Institute, Carnegie- Mel10n University, Pittburgh, PA (April 1984). Dreschler + Nagel 82b : Volumetrie Model and 3D-Trajectory of a Moving Car Derived /rom Monocular TV Frame Sequences of aStreet Scene, L. Dreschler und H.-H. Nagel, Computer Graphics and Image Processing 20, 199--228 (1982).

Die Autoren geben eine fundierte Einführung in die Informatik, die von Anfang an die Zusammenhänge zwischen den Teilgebieten des Faches betont. Das Buch ist kompakt, weil der gemeinsame Kern der verschiedenen Informatikgebiete betrachtet wird. In einer integrativen Sichtweise werden Modellierung, abstrakte Datentypen, Algorithmen sowie nebenläufige und verteilte Programmierung behandelt. Die grundlegenden Konzepte der Informatik werden dabei mittels der Programmiersprache Java realisiert. Wesentliches Anliegen der Autoren ist es, die Informatik als Wissenschaft der Abstraktion herauszustellen und in diesem Sinne den Studierenden allgemeine Methoden zum Lösen praktischer Probleme zu vermitteln.Lernkontrollen und ein effektiver Index, der vor allem diejenigen Begriffe aufführt, die ein Informatiker einfach können muss, ermöglichen ein fokussiertes Studium. Ferner stehen vielfältige Programm-Beispiele im Internet bereit.

Introduction The dramatic increase in available computer storage capacity over the last 10 years has led to the creation of very large databases of scienti?c and commercial information. The need to analyze these masses of data has led to the evolution of the new ?eld knowledge discovery in databases (KDD) at the intersection of machine learning, statistics and database technology. Being interdisciplinary by nature, the ?eld o?ers the opportunity to combine the expertise of di?erent ?elds intoacommonobjective.Moreover,withineach?elddiversemethodshave been developed and justi?ed with respect to di?erent quality criteria. We have toinvestigatehowthesemethods cancontributeto solvingthe problemofKDD. Traditionally, KDD was seeking to ?nd global models for the data that - plain most of the instances of the database and describe the general structure of the data. Examples are statistical time series models, cluster models, logic programs with high coverageor classi?cation models like decision trees or linear decision functions. In practice, though, the use of these models often is very l- ited, because global models tend to ?nd only the obvious patterns in the data, 1 which domain experts already are aware of . What is really of interest to the users are the local patterns that deviate from the already-known background knowledge. David Hand, who organized a workshop in 2002, proposed the new ?eld of local patterns.

Machine learning has become a rapidly growing field of Artificial Intelligence. Since the First International Workshop on Machine Learning in 1980, the number of scientists working in the field has been increasing steadily. This situation allows for specialization within the field. There are two types of specialization: on subfields or, orthogonal to them, on special subjects of interest. This book follows the thematic orientation. It contains research papers, each of which throws light upon the relation between knowledge representation, knowledge acquisition and machine learning from a different angle. Building up appropriate representations is considered to be the main concern of knowledge acquisition for knowledge-based systems throughout the book. Here machine learning is presented as a tool for building up such representations. But machine learning itself also states new representational problems. This book gives an easy-to-understand insight into a new field with its problems and the solutions it offers. Thus it will be of good use to both experts and newcomers to the subject.