About this product

Product Identifiers

PublisherNow Publishers

ISBN-101680838806

ISBN-139781680838800

eBay Product ID (ePID)2321450291

Product Key Features

Number of Pages102 Pages

Publication NameTrends in Explanations : Understanding and Debugging Data-Driven Systems

LanguageEnglish

SubjectComputer Science, General, Databases / Servers

Publication Year2021

TypeTextbook

AuthorAlexandra Meliou, Boris Glavic, Sudeepa Roy

Subject AreaMathematics, Computers

SeriesFoundations and Trends in Databases Ser.

FormatTrade Paperback

Dimensions

Item Weight5.5 Oz

Item Length9.2 in

Item Width6.1 in

Additional Product Features

Intended AudienceScholarly & Professional

Dewey Edition23

IllustratedYes

Dewey Decimal005.437

Table Of Content1. Introduction2. Explanation Needs: Who, Why, and What3. Explanations and Methodologies: How4. A Research RoadmapAcknowledgementsReferences

SynopsisThis book provides researchers and system developers with a high-level overview of the complex problems encountered when developing better user interaction with modern large-scale data-driven computing systems and describes a roadmap to solving these issues in the future., The increasing complexity of systems and technologies in everyday use, make it hard or even impossible for humans to comprehend their function and behavior, and justify surprising observations. Explanation support can ease humans' interactions with technology: explanations can help users understand a system's function, justify system results, and increase their trust in automated decisions.In this book the authors provide an overview of existing work in explanation support for data-driven processes. In doing so, they classify explainability requirements across three dimensions: the target of the explanation ("What"), the audience of the explanation ("Who"), and the purpose of the explanation ("Why"). They identify dominant themes across these dimensions and the high-level desiderata each implies, accompanied by several examples to motivate various problem settings. Finally, they discuss explainability solutions through the lens of the "How" dimension: How something is explained (the form of the explanation) and how explanations are derived (methodology). This book provides researchers and system developers with a high-level overview of the complex problems encountered when developing better user interaction with modern large-scale data-driven computing systems and describes a roadmap to solving these issues in the future., The increasing complexity of systems and technologies in everyday use, make it hard or even impossible for humans to comprehend their function and behavior, and justify surprising observations. Explanation support can ease humans' interactions with technology: explanations can help users understand a system's function, justify system results, and increase their trust in automated decisions. In this book the authors provide an overview of existing work in explanation support for data-driven processes. In doing so, they classify explainability requirements across three dimensions: the target of the explanation ("What"), the audience of the explanation ("Who"), and the purpose of the explanation ("Why"). They identify dominant themes across these dimensions and the high-level desiderata each implies, accompanied by several examples to motivate various problem settings. Finally, they discuss explainability solutions through the lens of the "How" dimension: How something is explained (the form of the explanation) and how explanations are derived (methodology). This book provides researchers and system developers with a high-level overview of the complex problems encountered when developing better user interaction with modern large-scale data-driven computing systems and describes a roadmap to solving these issues in the future.

LC Classification NumberQA76.9.U83