Explainable AI: Interpreting, Explaining and Visualizing Deep Learning
Mentés helye:
Testületi szerző: | |
---|---|
Közreműködő(k): | |
Különgyűjtemény: | e-book |
Formátum: | könyv |
Nyelv: | angol |
Megjelenés: |
Cham : Springer International Publishing,
2019
|
Sorozat: | Lecture Notes in Artificial Intelligence ; 11700 |
Tárgyszavak: | |
Online elérés: | http://doi.org/10.1007/978-3-030-28954-6 |
Címkék: |
Új címke
A tételhez itt fűzhet saját címkét!
|
id |
opac-EUL01-001013695 |
---|---|
collection |
e-book |
institution |
L_042 EUL01 |
spelling |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning edited by Wojciech Samek [et al.] Cham Springer International Publishing 2019 XI, 439 p. online forrás szöveg txt rdacontent számítógépes c rdamedia távoli hozzáférés cr rdacarrier szövegfájl PDF rda Lecture Notes in Artificial Intelligence 11700 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. Nyomtatott kiadás: ISBN 9783030289539 Nyomtatott kiadás: ISBN 9783030289553 Az e-könyvek a teljes ELTE IP-tartományon belül online elérhetők. e-book könyv számítógépes látás informatika EUL10000467497 Y gépi látás informatika EUL10001008247 Y neurális hálózatok mesterséges intelligencia EUL10000965239 Y fuzzy-rendszerek EUL10000250526 Y képfeldolgozás EUL10000446595 Y számítógépes biztonság EUL10000488943 Y Artificial intelligence. EUL10000183324 Y Optical data processing. Computers. EUL10000049752 Y Computer security. EUL10000344503 Y Computer organization. EUL10000373746 Y elektronikus könyv Samek, Wojciech. szerk. EUL10001092284 Y SpringerLink (Online service) közreadó testület Lecture Notes in Artificial Intelligence Online változat http://doi.org/10.1007/978-3-030-28954-6 Cham Springer International Publishing Imprint: Springer 2019 EUL01 |
language |
English |
format |
Book |
author2 |
Samek, Wojciech., szerk. |
author_facet |
Samek, Wojciech., szerk. SpringerLink (Online service), közreadó testület |
author_corporate |
SpringerLink (Online service), közreadó testület |
author_sort |
Samek, Wojciech. |
title |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning |
spellingShingle |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning Lecture Notes in Artificial Intelligence ; 11700 számítógépes látás -- informatika gépi látás -- informatika neurális hálózatok -- mesterséges intelligencia fuzzy-rendszerek képfeldolgozás számítógépes biztonság Artificial intelligence. Optical data processing. Computers. Computer security. Computer organization. elektronikus könyv |
title_short |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning |
title_full |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning edited by Wojciech Samek [et al.] |
title_fullStr |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning edited by Wojciech Samek [et al.] |
title_full_unstemmed |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning edited by Wojciech Samek [et al.] |
title_auth |
Explainable AI: Interpreting, Explaining and Visualizing Deep Learning |
title_sort |
explainable ai interpreting explaining and visualizing deep learning |
series |
Lecture Notes in Artificial Intelligence ; 11700 |
series2 |
Lecture Notes in Artificial Intelligence |
publishDate |
2019 |
publishDateSort |
2019 |
physical |
XI, 439 p. : online forrás |
isbn |
978-3-030-28954-6 |
callnumber-first |
Q - Science |
callnumber-subject |
Q - General Science |
callnumber-label |
Q334-342 |
callnumber-raw |
15929 |
callnumber-search |
15929 |
topic |
számítógépes látás -- informatika gépi látás -- informatika neurális hálózatok -- mesterséges intelligencia fuzzy-rendszerek képfeldolgozás számítógépes biztonság Artificial intelligence. Optical data processing. Computers. Computer security. Computer organization. elektronikus könyv |
topic_facet |
számítógépes látás -- informatika gépi látás -- informatika neurális hálózatok -- mesterséges intelligencia fuzzy-rendszerek képfeldolgozás számítógépes biztonság Artificial intelligence. Optical data processing. Computers. Computer security. Computer organization. elektronikus könyv számítógépes látás gépi látás neurális hálózatok fuzzy-rendszerek képfeldolgozás számítógépes biztonság Artificial intelligence. Optical data processing. Computers. Computer security. Computer organization. informatika mesterséges intelligencia |
url |
http://doi.org/10.1007/978-3-030-28954-6 |
illustrated |
Illustrated |
dewey-hundreds |
000 - Computer science, information & general works |
dewey-tens |
000 - Computer science, knowledge & systems |
dewey-ones |
006 - Special computer methods |
dewey-full |
006.3 |
dewey-sort |
16.3 |
dewey-raw |
006.3 |
dewey-search |
006.3 |
first_indexed |
2023-12-27T14:34:21Z |
last_indexed |
2023-12-29T20:06:33Z |
recordtype |
opac |
publisher |
Cham : Springer International Publishing |
_version_ |
1786644313017417728 |
score |
13,371168 |
generalnotes |
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. |