KI 2022: Advances in Artificial Intelligence 45th German Conference on AI, Trier, Germany, September 19–23, 2022, Proceedings

This book constitutes the refereed proceedings of the 45^th German Conference on Artificial Intelligence, KI 2022, held in September 2022.

The 12 full and 5 short papers were carefully reviewed and selected from 51 submissions. Additionally, five abstracts of invited talks are included. As well-established annual conference series KI is dedicated to research on theory and applications across all methods and topic areas of AI research.

Due to COVID-19 the conference was held virtually.

The chapter "Dynamically Self-Adjusting Gaussian Processes for Data Stream Modelling" is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com.

An Implementation of Nonmonotonic Reasoning with System W.- Leveraging implicit gaze-based user feedback for interactive machine learning.- The Randomness of Input Data Spaces is an A Priori Predictor for Generalization.- Communicating Safety of Planned Paths via Optimally-Simple Explanations.- Assessing the Accuracy-Explainability-Cost Trade-off on Model Selection for Retail Article Categorization.- Enabling Supervised Machine Learning for SMEs through Data Pooling: A Case Study in the Service Industry.- Unsupervised Alignment of Distributional Word Embeddings. NeuralPDE: Modelling Dynamical Systems from Data.- Deep Neural Networks for Geometric Shape Deformation.- Dynamically Self-Adjusting Gaussian Processes for Data Stream Modelling.- Optimal Fixed-Premise Repairs of EL TBoxes.- Health And Habit: an Agent-based Approach.- Knowledge Graph Embeddings with Ontologies: Reification for Representing Arbitrary Relations.- Solving the Traveling Salesperson Problem with Precedence Constraints by Deep Reinforcement Learning.- HanKA: Enriched Knowledge Used by an Adaptive Cooking Assistant.- Automated Kantian Ethics: A Faithful Implementation and Testing Framework.- PEBAM: A Profile-based Evaluation Method for Bias Assessment on Mixed Datasets.