
KI 2020: Advances in Artificial Intelligence
Description
Alles über E-Books | Antworten auf Fragen rund um E-Books, Kopierschutz und Dateiformate finden Sie in unserem Info- & Hilfebereich.
The 16 full and 12 short papers presented together with 6 extended abstracts in this volume were carefully reviewed and selected from 62 submissions.
As well-established annual conference series KI is dedicated to research on theory and applications across all methods and topic areas of AI research. KI 2020 had a special focus on human-centered AI with highlights on AI and education and explainable machine learning.
Due to the Corona pandemic KI 2020 was held as a virtual event.
More details
Other editions
Additional editions

Content
Two Algorithms for Additive and Fair Division of Mixed Manna.- Dynamic Play via Suit Factorization Search in Skat.- Dynamic Channel and Layer Gating in Convolutional Neural Network.- Contour-based Segmentation of Historical Printings.- Hybrid Ranking and Regression for Algorithm Selection.- Conditional Reasoning and Relevance.- HTN Plan Repair via Model Transformation.- Nonmonotonic Inferences with Qualitative Conditionals Based on Preferred Structures on Worlds.- Positive Free Higher-Order Logic and its Automation via a Semantical Embedding.- Low-Rank Subspace Override for Unsupervised Domain Adaptation.- Expressive Explanations of DNNs by Combining Concept Analysis with ILP.- Stable Resolving - A Randomized Local Search Heuristic for MaxSAT.- A Virtual Caregiver for Assisted Daily Living of Pre-Frail Users.- Exploring the Effects of Role Design on Agent Learning.- Descriptor Revision for Conditionals: Literal Descriptors and Conditional Preservation.- Multi-Agent Path Finding Modulo Theory with Continuous Movements and the Sum of Costs Objective.- Meta-Induction, Probability Aggregation, and Optimal Scoring.- Cones, Negation, and All That.- Swarm-based Cluster Analysis for Knowledge Discovery.- Draw with Me: Human-in-the-Loop for Image Restoration.- Reasonable Machines: A Research Manifesto.- A Heuristic Agent in Multi-Agent Path Finding Under Destination Uncertainty.- Earnings Prediction with Deep Leaning.- Integrating Keywords into BERT4Rec for Sequential Recommendation.- Modelling and Reasoning in Biomedical Applications with Qualitative Conditional Logic.- Conformal Rule-Based Multi-label Classification.- Optimizing Constraint Satisfaction Problems by Regularization for the Sample Case of the Warehouse Location Problem.- Fast Pathfinding in Knowledge Graphs Using Word Embeddings.- A Visually Explainable Learning System for Skin Lesion Detection Using Multiscale Input with Attention U-Net.- Evaluation of Deep Learning Accelerators for Object Detection at theEdge.-Learning Choice Functions via Pareto-Embeddings.- Simulation-Based Validation of Robot Commands for Force-based Robot Motions.- Firefighter Virtual Reality Simulation for Personalized Stress Detection.- The AI Domain Definition Language (AIDDL) for Integrated Systems.
System requirements
File format: PDF
Copy protection: Watermark-DRM (Digital Rights Management)
System requirements:
- Computer (Windows; MacOS X; Linux): Use the free software Adobe Reader, Adobe Digital Editions, or any other PDF viewer of your choice (see eBook Help).
- Tablet/Smartphone (Android; iOS): Install the free app Adobe Digital Editions or another reading app for eBooks, e.g., PocketBook (see eBook Help).
- E-reader: Bookeen, Kobo, Pocketbook, Sony, Tolino and many more (only limited: Kindle).
The file format PDF always displays a book page identically on any hardware. This makes PDF suitable for complex layouts such as those used in textbooks and reference books (images, tables, columns, footnotes). Unfortunately, on the small screens of e-readers or smartphones, PDFs are rather annoying, requiring too much scrolling.
This eBook uses Watermark-DRM, a „soft” copy protection. This means that there are no technical restrictions to prevent illegal distribution. However, there is a personalised watermark embedded in the eBook that can be used to identify the purchaser of the eBook in the event of misuse and to provide evidence for legal purposes.
For more information, see our eBook Help page.