17 resultater (0,29077 sekunder)

Vis alle filtre

Mærke

Butik

Pris (EUR)

Nulstil filter

Produkter
Fra
Butikker

Machine Knowledge - Gerhard Weikum - Bog - now publishers Inc - Plusbog.dk

Machine Knowledge - Gerhard Weikum - Bog - now publishers Inc - Plusbog.dk

Equipping machines with comprehensive knowledge of the world’s entities and their relationships has been a longstanding goal of AI. Over the last decade, large-scale knowledge bases, also known as knowledge graphs, have been automatically constructed from web contents and text sources,and have become a key asset for search engines. This machine knowledge can be harnessed to semantically interpret textual phrases in news, social media and web tables, and contributes to question answering, natural language processing and data analytics.This monograph surveys fundamental concepts and practical methods for creating and curating large knowledge bases. It covers models and methods for discovering and curating large knowledge bases from online content, with emphasis on semi-structured web pages with lists, tables etc., and unstructured text sources. Case studies on academic projects and industrial knowledge graphs complement the survey of concepts and methods.The intended audience is students and researchers interested in a wide spectrum of topics: from machine knowledge and data quality to machine learning and data science as well as applications in web content mining and natural language understanding. It will also be of interest to industrial practitioners working on semantic technologies for web, social media, or enterprise content.

DKK 574.00
1

SpiNNaker - A Spiking Neural Network Architecture - - Bog - now publishers Inc - Plusbog.dk

SpiNNaker - A Spiking Neural Network Architecture - - Bog - now publishers Inc - Plusbog.dk

20 years in conception and 15 in construction, the SpiNNaker project has delivered the world’s largest neuromorphic computing platform incorporating over a million ARM mobile phone processors and capable of modelling spiking neural networks of the scale of a mouse brain in biological real time. This machine, hosted at the University of Manchester in the UK, is freely available under the auspices of the EU Flagship Human Brain Project. This book tells the story of the origins of the machine, its development and its deployment, and the immense software development effort that has gone into making it openly available and accessible to researchers and students the world over. It also presents exemplar applications from ‘Talk’, a SpiNNaker-controlled robotic exhibit at the Manchester Art Gallery as part of ‘The Imitation Game’, a set of works commissioned in 2016 in honour of Alan Turing, through to a way to solve hard computing problems using stochastic neural networks. The book concludes with a look to the future, and the SpiNNaker-2 machine which is yet to come.

DKK 684.00
1

Kernel Mean Embedding of Distributions - Bharath Sriperumbudur - Bog - now publishers Inc - Plusbog.dk

Kernel Mean Embedding of Distributions - Bharath Sriperumbudur - Bog - now publishers Inc - Plusbog.dk

This monograph provides a comprehensive review of kernel mean embeddings of distributions and, in the course of doing so, discusses some challenging issues that could potentially lead to new research directions. The targeted audience includes graduate students and researchers in machine learning and statistics who are interested in the theory and applications of kernel mean embeddings.

DKK 889.00
1

Graph Kernels - Bastian Rieck - Bog - now publishers Inc - Plusbog.dk

Graph Kernels - Bastian Rieck - Bog - now publishers Inc - Plusbog.dk

Among the data structures commonly used in machine learning, graphs are arguably one of the most general. Graphs allow the modelling of complex objects, each of which can be annotated by metadata. Nonetheless, seemingly simple questions, such as determining whether two graphs are identical or whether one graph is contained in another graph, are remarkably hard to solve in practice. Machine learning methods operating on graphs must therefore grapple with the need to balance computational tractability with the ability to leverage as much of the information conveyed by each graph as possible. In the last 15 years, numerous graph kernels have been proposed to solve this problem, thereby making it possible to perform predictions in both classification and regression settings.This monograph provides a review of existing graph kernels, their applications, software plus data resources, and an empirical comparison of state-of-the-art graph kernels. It is divided into two parts: the first part focuses on the theoretical description of common graph kernels; the second part focuses on a large-scale empirical evaluation of graph kernels, as well as a description of desirable properties and requirements for benchmark data sets. Finally, the authors outline the future trends and open challenges for graph kernels.Written for every researcher, practitioner and student of machine learning, Graph Kernels provides a comprehensive and insightful survey of the various graph kernals available today. It gives the reader a detailed typology, and analysis of relevant graph kernels while exposing the relations between them and commenting on their applicability for specific data types. There is also a large-scale empirical evaluation of graph kernels.

DKK 628.00
1

Algorithmic Aspects of Parallel Data Processing - Dan Suciu - Bog - now publishers Inc - Plusbog.dk

Algorithmic Aspects of Parallel Data Processing - Dan Suciu - Bog - now publishers Inc - Plusbog.dk

The last decade has seen a huge and growing interest in processing large data sets on large distributed clusters. This trend began with the MapReduce framework, and has been widely adopted by several other systems, including PigLatin, Hive, Scope, Dremmel, Spark and Myria to name a few. While the applications of such systems are diverse (for example, machine learning, data analytics), most involve relatively standard data processing tasks like identifying relevant data, cleaning, filtering, joining, grouping, transforming, extracting features, and evaluating results. This has generated great interest in the study of algorithms for data processing on large distributed clusters.Algorithmic Aspects of Parallel Data Processing discusses recent algorithmic developments for distributed data processing. It uses a theoretical model of parallel processing called the Massively Parallel Computation (MPC) model, which is a simplification of the BSP model where the only cost is given by the amount of communication and the number of communication rounds. The survey studies several algorithms for multi-join queries, sorting, and matrix multiplication. It discusses their relationships and common techniques applied across the different data processing tasks.

DKK 850.00
1

Optimization with Sparsity-Inducing Penalties - Francis Bach - Bog - now publishers Inc - Plusbog.dk

Optimization with Sparsity-Inducing Penalties - Francis Bach - Bog - now publishers Inc - Plusbog.dk

Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. They were first dedicated to linear variable selection but numerous extensions have now emerged such as structured sparsity or kernel selection. It turns out that many of the related estimation problems can be cast as convex optimization problems by regularizing the empirical risk with appropriate nonsmooth norms. Optimization with Sparsity-Inducing Penalties presents optimization tools and techniques dedicated to such sparsity-inducing penalties from a general perspective. It covers proximal methods, block-coordinate descent, reweighted ?2-penalized techniques, working-set and homotopy methods, as well as non-convex formulations and extensions, and provides an extensive set of experiments to compare various algorithms from a computational point of view. The presentation of Optimization with Sparsity-Inducing Penalties is essentially based on existing literature, but the process of constructing a general framework leads naturally to new results, connections and points of view. It is an ideal reference on the topic for anyone working in machine learning and related areas.

DKK 732.00
1

An Algorithmic Perspective on Imitation Learning - Gerhard Neumann - Bog - now publishers Inc - Plusbog.dk

An Algorithmic Perspective on Imitation Learning - Gerhard Neumann - Bog - now publishers Inc - Plusbog.dk

As robots and other intelligent agents move from simple environments and problems to more complex, unstructured settings, manually programming their behavior has become increasingly challenging and expensive. Often, it is easier for a teacher to demonstrate a desired behavior rather than attempt to manually engineer it. This process of learning from demonstrations, and the study of algorithms to do so, is called imitation learning.An Algorithmic Perspective on Imitation Learning provides the reader with an introduction to imitation learning. It covers the underlying assumptions, approaches, and how they relate; the rich set of algorithms developed to tackle the problem; and advice on effective tools and implementation.An Algorithmic Perspective on Imitation Learning serves two audiences. First, it familiarizes machine learning experts with the challenges of imitation learning, particularly those arising in robotics, and the interesting theoretical and practical distinctions between it and more familiar frameworks like statistical supervised learning theory and reinforcement learning. Second, it provides roboticists and experts in applied artificial intelligence with a broader appreciation for the frameworks and tools available for imitation learning. It pays particular attention to the intimate connection between imitation learning approaches and those of structured prediction.

DKK 889.00
1

Spectral Learning on Matrices and Tensors - Majid Janzamin - Bog - now publishers Inc - Plusbog.dk

Spectral Learning on Matrices and Tensors - Majid Janzamin - Bog - now publishers Inc - Plusbog.dk

The authors of this monograph survey recent progress in using spectral methods including matrix and tensor decomposition techniques to learn many popular latent variable models. With careful implementation, tensor-based methods can run efficiently in practice, and in many cases they are the only algorithms with provable guarantees on running time and sample complexity. The focus is on a special type of tensor decomposition called CP decomposition, and the authors cover a wide range of algorithms to find the components of such tensor decomposition. They also discuss the usefulness of this decomposition by reviewing several probabilistic models that can be learned using such tensor methods. The second half of the monograph looks at practical applications. This includes using Tensorly, an efficient tensor algebra software package, which has a simple python interface for expressing tensor operations. It also has a flexible back-end system supporting NumPy, PyTorch, TensorFlow, and MXNet. Spectral Learning on Matrices and Tensors provides a theoretical and practical introduction to designing and deploying spectral learning on both matrices and tensors. It is of interest for all students, researchers and practitioners working on modern day machine learning problems.

DKK 889.00
1

QED at Large - Milos Gligoric - Bog - now publishers Inc - Plusbog.dk

QED at Large - Milos Gligoric - Bog - now publishers Inc - Plusbog.dk

Development of formal proofs of correctness of programs can increase actual and perceived reliability and facilitate better understanding of program specifications and their underlying assumptions. Tools supporting such development have been available for over 40 years but have only recently seen wide practical use. Projects based on construction of machine-checked formal proofs are now reaching an unprecedented scale, comparable to large software projects, which leads to new challenges in proof development and maintenance. Despite its increasing importance, the field of proof engineering is seldom considered in its own right; related theories, techniques, and tools span many fields and venues.QED at Large covers the timeline and research literature concerning proof development for program verification, including theories, languages, and tools. It emphasizes challenges and breakthroughs at each stage in history and highlights challenges that are currently present due to the increasing scale of proof developments.This monograph is intended for use by researchers and students who are new to the field. It provides the reader with an insightful overview of the work that has led to modern-day techniques for formally verifying software. In times of increasing automation, this underpins many software systems so future trends are also highlighted.

DKK 630.00
1

Sparsity Methods for Systems and Control - Masaaki Nagahara - Bog - now publishers Inc - Plusbog.dk

Sparsity Methods for Systems and Control - Masaaki Nagahara - Bog - now publishers Inc - Plusbog.dk

The method of sparsity has been attracting a lot of attention in the fields related not only to signal processing, machine learning, and statistics, but also systems and control. The method is known as compressed sensing, compressive sampling, sparse representation, or sparse modeling. More recently, the sparsity method has been applied to systems and control to design resource-aware control systems. This book gives a comprehensive guide to sparsity methods for systems and control, from standard sparsity methods in finite-dimensional vector spaces (Part I) to optimal control methods in infinite-dimensional function spaces (Part II).The primary objective of this book is to show how to use sparsity methods for several engineering problems. For this, the author provides MATLAB programs by which the reader can try sparsity methods for themselves. Readers will obtain a deep understanding of sparsity methods by running these MATLAB programs. Sparsity Methods for Systems and Control is suitable for graduate level university courses, though it should also be comprehendible to undergraduate students who have a basic knowledge of linear algebra and elementary calculus. Also, especially part II of the book should appeal to professional researchers and engineers who are interested in applying sparsity methods to systems and control.

DKK 899.00
1

Human-Robot Interaction - Michael A. Goodrich - Bog - now publishers Inc - Plusbog.dk

Human-Robot Interaction - Michael A. Goodrich - Bog - now publishers Inc - Plusbog.dk

Human-Robot Interaction: A Survey presents a unified treatment of HRI-related issues, identifies key themes, and discusses challenge problems that are likely to shape the field in the near future. The authors describe the HRI story from multiple perspectives with an eye toward identifying themes that cross applications. The survey includes research results from a cross section of the universities, government efforts, industry labs, and countries that contribute to HRI, and a cross section of the disciplines that contribute to the field, such as human factors, robotics, cognitive psychology and design. Human-Robot Interaction: A Survey starts out by tracing the early history of robotics and human-machine interaction and the emergence of HRI as a field in its own right. It goes on to discuss what defines an HRI problem and to survey the kinds of problems encountered. The final two sections focus on the accepted practices, challenge problems and solution themes that have emerged as the field has matured. It concludes with a section on how HRI research ties in with work in other scientific fields. Human-Robot Interaction: A Survey is both an ideal tutorial for people outside the field and a timely addition to the current literature within the field which is intended to promote discussion of a unified vision of HRI

DKK 682.00
1

Security Risk Management for the Internet of Things - - Bog - now publishers Inc - Plusbog.dk

Security Risk Management for the Internet of Things - - Bog - now publishers Inc - Plusbog.dk

In recent years, the rising complexity of Internet of Things (IoT) systems has increased their potential vulnerabilities and introduced new cybersecurity challenges. In this context, state of the art methods and technologies for security risk assessment have prominent limitations when it comes to large scale, cyber-physical and interconnected IoT systems. Risk assessments for modern IoT systems must be frequent, dynamic and driven by knowledge about both cyber and physical assets. Furthermore, they should be more proactive, more automated, and able to leverage information shared across IoT value chains.This book introduces a set of novel risk assessment techniques and their role in the IoT Security risk management process. Specifically, it presents architectures and platforms for end-to-end security, including their implementation based on the edge/fog computing paradigm. It also highlights machine learning techniques that boost the automation and proactiveness of IoT security risk assessments. Furthermore, blockchain solutions for open and transparent sharing of IoT security information across the supply chain are introduced. Frameworks for privacy awareness, along with technical measures that enable privacy risk assessment and boost GDPR compliance are also presented. Likewise, the book illustrates novel solutions for security certification of IoT systems, along with techniques for IoT security interoperability.In the coming years, IoT security will be a challenging, yet very exciting journey for IoT stakeholders, including security experts, consultants, security research organizations and IoT solution providers. The book provides knowledge and insights about where we stand on this journey. It also attempts to develop a vision for the future and to help readers start their IoT Security efforts on the right foot.

DKK 1049.00
1

Cyber-Physical Threat Intelligence for Critical Infrastructures Security - - Bog - now publishers Inc - Plusbog.dk

Cyber-Physical Threat Intelligence for Critical Infrastructures Security - - Bog - now publishers Inc - Plusbog.dk

Modern critical infrastructures comprise of many interconnected cyber and physical assets, and as such are large scale cyber-physical systems. Hence, the conventional approach of securing these infrastructures by addressing cyber security and physical security separately is no longer effective. Rather more integrated approaches that address the security of cyber and physical assets at the same time are required. This book presents integrated (i.e. cyber and physical) security approaches and technologies for the critical infrastructures that underpin our societies. Specifically, it introduces advanced techniques for threat detection, risk assessment and security information sharing, based on leading edge technologies like machine learning, security knowledge modelling, IoT security and distributed ledger infrastructures. Likewise, it presets how established security technologies like Security Information and Event Management (SIEM), pen-testing, vulnerability assessment and security data analytics can be used in the context of integrated Critical Infrastructure Protection.The novel methods and techniques of the book are exemplified in case studies involving critical infrastructures in four industrial sectors, namely finance, healthcare, energy and communications. The peculiarities of critical infrastructure protection in each one of these sectors is discussed and addressed based on sector-specific solutions.The advent of the fourth industrial revolution (Industry 4.0) is expected to increase the cyber-physical nature of critical infrastructures as well as their interconnection in the scope of sectorial and cross-sector value chains. Therefore, the demand for solutions that foster the interplay between cyber and physical security, and enable Cyber-Physical Threat Intelligence is likely to explode. In this book, we have shed light on the structure of such integrated security systems, as well as on the technologies that will underpin their operation. We hope that Security and Critical Infrastructure Protection stakeholders will find the book useful when planning their future security strategies.

DKK 1049.00
1