05908nam 22007335 450 991034929950332120211006184241.03-030-28954-010.1007/978-3-030-28954-6(CKB)4100000009191108(DE-He213)978-3-030-28954-6(MiAaPQ)EBC5927126(PPN)248601466(EXLCZ)99410000000919110820190829d2019 u| 0engurnn#008mamaatxtrdacontentcrdamediacrrdacarrierExplainable AI: Interpreting, Explaining and Visualizing Deep Learning /edited by Wojciech Samek, Grégoire Montavon, Andrea Vedaldi, Lars Kai Hansen, Klaus-Robert Müller1st ed. 2019.Cham :Springer International Publishing :Imprint: Springer,2019.1 online resource (XI, 439 p. 152 illus., 119 illus. in color.)Lecture Notes in Artificial Intelligence ;117003-030-28953-2 Includes bibliographical references and index.Towards Explainable Artificial Intelligence -- Transparency: Motivations and Challenges -- Interpretability in Intelligent Systems: A New Concept? -- Understanding Neural Networks via Feature Visualization: A Survey -- Interpretable Text-to-Image Synthesis with Hierarchical Semantic Layout Generation -- Unsupervised Discrete Representation Learning -- Towards Reverse-Engineering Black-Box Neural Networks -- Explanations for Attributing Deep Neural Network Predictions -- Gradient-Based Attribution Methods -- Layer-Wise Relevance Propagation: An Overview -- Explaining and Interpreting LSTMs -- Comparing the Interpretability of Deep Networks via Network Dissection -- Gradient-Based vs. Propagation-Based Explanations: An Axiomatic Comparison -- The (Un)reliability of Saliency Methods -- Visual Scene Understanding for Autonomous Driving Using Semantic Segmentation -- Understanding Patch-Based Learning of Video Data by Explaining Predictions -- Quantum-Chemical Insights from Interpretable Atomistic Neural Networks -- Interpretable Deep Learning in Drug Discovery -- Neural Hydrology: Interpreting LSTMs in Hydrology -- Feature Fallacy: Complications with Interpreting Linear Decoding Weights in fMRI -- Current Advances in Neural Decoding -- Software and Application Patterns for Explanation Methods.The development of “intelligent” systems that can take decisions and perform autonomously might lead to faster and more consistent decisions. A limiting factor for a broader adoption of AI technology is the inherent risks that come with giving up human control and oversight to “intelligent” machines. Forsensitive tasks involving critical infrastructures and affecting human well-being or health, it is crucial to limit the possibility of improper, non-robust and unsafe decisions and actions. Before deploying an AI system, we see a strong need to validate its behavior, and thus establish guarantees that it will continue to perform as expected when deployed in a real-world environment. In pursuit of that objective, ways for humans to verify the agreement between the AI decision structure and their own ground-truth knowledge have been explored. Explainable AI (XAI) has developed as a subfield of AI, focused on exposing complex AI models to humans in a systematic and interpretable manner. The 22 chapters included in this book provide a timely snapshot of algorithms, theory, and applications of interpretable and explainable AI and AI techniques that have been proposed recently reflecting the current discourse in this field and providing directions of future development. The book is organized in six parts: towards AI transparency; methods for interpreting AI systems; explaining the decisions of AI systems; evaluating interpretability and explanations; applications of explainable AI; and software for explainable AI.Lecture Notes in Artificial Intelligence ;11700Artificial intelligenceOptical data processingComputersComputer securityComputer organizationArtificial Intelligencehttps://scigraph.springernature.com/ontologies/product-market-codes/I21000Image Processing and Computer Visionhttps://scigraph.springernature.com/ontologies/product-market-codes/I22021Computing Milieuxhttps://scigraph.springernature.com/ontologies/product-market-codes/I24008Systems and Data Securityhttps://scigraph.springernature.com/ontologies/product-market-codes/I28060Computer Systems Organization and Communication Networkshttps://scigraph.springernature.com/ontologies/product-market-codes/I13006Artificial intelligence.Optical data processing.Computers.Computer security.Computer organization.Artificial Intelligence.Image Processing and Computer Vision.Computing Milieux.Systems and Data Security.Computer Systems Organization and Communication Networks.006.32006.3Samek Wojciechedthttp://id.loc.gov/vocabulary/relators/edtMontavon Grégoireedthttp://id.loc.gov/vocabulary/relators/edtVedaldi Andreaedthttp://id.loc.gov/vocabulary/relators/edtHansen Lars Kaiedthttp://id.loc.gov/vocabulary/relators/edtMüller Klaus-Robertedthttp://id.loc.gov/vocabulary/relators/edtMiAaPQMiAaPQMiAaPQBOOK9910349299503321Explainable AI2821265UNINA