Skip to main content

KI - Künstliche Intelligenz OnlineFirst articles

Open Access 21.06.2024 | Technical Contribution

AI in Healthcare and the Public Sector: How to Face the Challenges of High-Risk Applications and What AI Research Can Get Out of It

Application projects, may it be in healthcare and the public sector or elsewhere, have the potential to advance foundational (“genuine”) artificial intelligence (AI) research. Unfortunately, insights from specific application projects are rarely …

verfasst von:
Tanya Braun, Ralf Möller

Open Access 20.06.2024 | Technical Contribution

AI in Healthcare and the Public Sector

This special issue covers a variety of topics within the area of AI in healthcare and the public sector, with four technical contributions, five project reports, a system description, and two dissertation abstracts, next to a survey that also …

verfasst von:
Tanya Braun, Ralf Möller

Open Access 13.06.2024 | Technical Contribution

Lifting in Support of Privacy-Preserving Probabilistic Inference

Privacy-preserving inference aims to avoid revealing identifying information about individuals during inference. Lifted probabilistic inference works with groups of indistinguishable individuals, which has the potential to prevent tracing back a …

verfasst von:
Marcel Gehrke, Johannes Liebenow, Esfandiar Mohammadi, Tanya Braun

Open Access 12.06.2024 | Technical Contribution

Partial Image Active Annotation (PIAA): An Efficient Active Learning Technique Using Edge Information in Limited Data Scenarios

Active learning (AL) algorithms are increasingly being used to train models with limited data for annotation tasks. However, the selection of data for AL is a complex issue due to the restricted information on unseen data. To tackle this problem …

verfasst von:
Md Abdul Kadir, Hasan Md Tusfiqur Alam, Devansh Srivastav, Hans-Jürgen Profitlich, Daniel Sonntag

24.05.2024 | Technical Contribution

Modeling Family Logics for Artificial Intelligence: Doxastic-Temporal Logics for Reasoning About Goals

We introduce the $$\mathscr {C}^{0}$$ C 0 family of logics, which include temporalized modal operators for belief and hyperintensional modal operators for obligations and goals. We motivate the $$\mathscr {C}^{0}$$ C 0 family as extended doxastic …

verfasst von:
James T. Oswald, Brandon Rozek, Thomas M. Ferguson

22.05.2024 | Systems Description

Spectra: An Expressive STRIPS-Inspired AI Planner Based on Automated Reasoning

(System Description)

Research in automated planning traditionally focuses on model-based approaches that often sacrifice expressivity for computational efficiency. For artificial agents that operate in complex environments, however, frequently the agent needs to …

verfasst von:
Brandon Rozek, Selmer Bringsjord

Open Access 05.05.2024 | Project Reports

Project VoLL-KI

Learning from Learners

“Learning from Learners” (“Von Lernenden Lernen”, “VoLL-KI ” for short) is a is collaborative research project with the goal of creating a practical toolbox of instruments at different levels of abstraction to improve the learning experience and …

verfasst von:
Michael Kohlhase, Marc Berges, Jens Grubert, Andreas Henrich, Dieter Landes, Jochen L. Leidner, Florian Mittag, Daniela Nicklas, Ute Schmid, Yvonne Sedlmaier, Achim Ulbrich-vom Ende, Diedrich Wolter

Open Access 03.05.2024 | Systems Description

CLKR: Conditional Logic and Knowledge Representation

CLKR (Conditional Logic and Knowledge Representation) is an online repository of conditional logic resources for knowledge representation and reasoning. The question which entailments should follow from a conditional knowledge base consisting of a …

verfasst von:
Christoph Beierle, Jonas Haldimann, Leon Schwarzer

Open Access 26.04.2024 | Dissertation and Habilitation Abstracts

Comprehensible Extraction of Knowledge Bases for Learning Agents in Games

This dissertation abstract summarizes results of the thesis “Comprehensible Knowledge Base Extraction for Learning Agents - Practical Challenges and Applications in Games” (accepted as dissertation at the Department of Computer Science of TU …

verfasst von:
Daan Apeldoorn

Open Access 18.04.2024 | Technical Contribution

Automated Computation of Therapies Using Failure Mode and Effects Analysis in the Medical Domain

Failure mode and effects analysis (FMEA) is a systematic approach to identify and analyse potential failures and their effects in a system or process. The FMEA approach, however, requires domain experts to manually analyse the FMEA model to derive …

verfasst von:
Malte Luttermann, Edgar Baake, Juljan Bouchagiar, Benjamin Gebel, Philipp Grüning, Dilini Manikwadura, Franziska Schollemann, Elisa Teifke, Philipp Rostalski, Ralf Möller

Open Access 16.04.2024 | Technical Contribution

Learning Normative Behaviour Through Automated Theorem Proving

Reinforcement learning (RL) is a powerful tool for teaching agents goal-directed behaviour in stochastic environments, and many proposed applications involve adopting societal roles which have ethical, legal, or social norms attached to them.

verfasst von:
Emery A. Neufeld

Open Access 16.04.2024 | Dissertation and Habilitation Abstracts

Towards a Logical Foundation of Randomized Computation: Doctoral Thesis Abstract

Interactions between logic and theoretical computer science are multiple and profound. In the last decades, they have been deeply investigated, but, surprisingly, the study of probabilistic computation was only marginally touched by such fruitful …

verfasst von:
Melissa Antonelli

26.03.2024 | Interview

Lessons from Resource-Aware Machine Learning for Healthcare: An Interview with Katharina Morik

verfasst von:
Tanya Braun, Ralf Möller

Open Access 06.03.2024 | Project Reports

Report on “Axiomatizing Conditional Normative Reasoning”

This is a report on the project “Axiomatizing Conditional Normative Reasoning” (ANCoR, M 3240-N) funded by the Austrian Science Fund (FWF). The project aims to deepen our understanding of conditional normative reasoning by providing an axiomatic …

verfasst von:
Xavier Parent

21.02.2024 | Project Reports

Building an AI Support Tool for Real-Time Ulcerative Colitis Diagnosis

Ulcerative Colitis (UC) is a chronic inflammatory bowel disease decreasing life quality through symptoms such as bloody diarrhoea and abdominal pain. Endoscopy is a cornerstone of diagnosis and monitoring of UC. The Mayo endoscopic subscore (MES) …

verfasst von:
Bjørn Leth Møller, Bobby Zhao Sheng Lo, Johan Burisch, Flemming Bendtsen, Ida Vind, Bulat Ibragimov, Christian Igel

Open Access 14.02.2024 | Project Reports

Human-Centered Explanations: Lessons Learned from Image Classification for Medical and Clinical Decision Making

To date, there is no universal explanatory method for making decisions of an AI-based system transparent to human decision makers. This is because, depending on the application domain, data modality, and classification model, the requirements for …

verfasst von:
Bettina Finzel

13.02.2024 | Technical Contribution

Colonoscopy Polyp Detection Using Bi-Directional Conv-LSTM U-Net with Densely Connected Convolution

Several researchers have focused in recent years on improving the efficiency of abdominal diagnostics by segmenting colonoscopy images with machine learning techniques. Previously, colonoscopy images were manually segmented by experts in this …

verfasst von:
Shweta Gangrade, Prakash Chandra Sharma, Akhilesh Kumar Sharma

Open Access 10.02.2024 | Dissertation and Habilitation Abstracts

Computer-Verified Foundations of Metaphysics

We report on recent successes in the application of computational methods and automated reasoning techniques to a foundational theory of metaphysics: in [ 13 ], we utilize and extend the method of shallow semantic embeddings (SSEs) in classical …

verfasst von:
Daniel Kirchner

Open Access 01.02.2024 | Dissertation and Habilitation Abstracts

Semantics of Belief Change Operators for Intelligent Agents

Iteration, Postulates, and Realizability

This paper summarises several contributions to the theory of belief change by the authors’ dissertation thesis. First, a relational characterization of belief revision for Tarskian logics is considered, encompassing first-order predicate logic …

verfasst von:
Kai Sauerwald

Open Access 22.01.2024 | Technical Contribution

Predicting Individual Treatment Effects: Challenges and Opportunities for Machine Learning and Artificial Intelligence

Personalized medicine seeks to identify the right treatment for the right patient at the right time. Predicting the treatment effect for an individual patient has the potential to transform treatment of patients and drastically improve patients …

verfasst von:
Thomas Jaki, Chi Chang, Alena Kuhlemeier, M. Lee Van Horn, The Pooled Resource Open-Access ALS Clinical Trials Consortium