KI - Künstliche Intelligenz
Publisher: Springer Nature · ISSN 0933-1875,1610-1987 · 55 articles
- Excellence as Driver of AI
-
A Retrospective on the Description Logic Reasoning System Racer
The system Racer is presented as a pragmatic introduction to description logic reasoning for readers without a formal background, focusing on real-world data interpretation scenarios. Illustrating why Racer was originally developed, the...
-
A Historical Perspective on the Development of Knowledge-Based Product Configuration Systems in Germany from 1985 to 2000
This article provides an overview of the evolution of knowledge-based configuration systems in Germany from the 1980s to the early 2000s. It traces the development from an expert system such as PLAKON and its variant $$\mu $$ PLAKON, to...
- From Machine Learning Theory to Sustainable AI
-
The Symbiosis Everyone Has Been Waiting For: Why Digital Twins and Agentic AI are Inseparable
Over the past decade, the Digital Twin paradigm has emerged as a cornerstone of industrial digitization. However, traditional Digital Twin deployments face a fundamental constraint. While modern Digital Twins incorporate active control...
- From Learning Machines to Responsible: AI
- Mathematical Foundations and Europe’s Strength
-
Neurosymbolic Robot Programming
Programming intelligent robots requires novel approaches that harness the learning abilities of deep neural architectures while allowing humans to specify, monitor and understand robot behavior. This dissertation conceptualizes robot...
-
StretchBot: A Neuro-Symbolic Framework for Adaptive Guidance with Assistive Robots
Assistive robots have growing potential to support physical wellbeing in home and healthcare settings, for example, by guiding users through stretching or rehabilitation routines. However, existing systems remain largely scripted, which...
- From Terminological Reasoning to Robot Soccer
-
Digital Twins as a Necessary Foundation for Deploying Physical AI on the Shop Floor
Public discourse on Physical AI is dominated by a promise of full autonomy: machines that perceive, learn, and act on their own. This paper argues that, for the foreseeable future, the industrial shop floor will not be fully autonomous...
-
From Academia to Industry: The Evolution and Impact of Clingo
Answer Set Programming (ASP) stands as a powerful, declarative paradigm within knowledge-driven AI, offering a robust framework for complex search and optimization. Unlike data-driven methods, ASP leverages explicit knowledge...
- From LOGO to Logic in AI
- From Symbolic Reasoning to Hybrid AI
- From Knowledge Bases to Cognitive Robotics
-
DESS: A Robust Uncertainty Layer for Embedding-Space Models
Embedding-space systems usually retrieve, rank, or recommend from a single point representation, even when the task would benefit from uncertainty or controlled diversity. We introduce DESS, a lightweight uncertainty layer that augments...
-
Agents Through the Ages
Over several decades, research on socially interactive agents has transformed human–machine interaction, evolving from early script-based systems to today’s generative, multimodal agents. Tracing this development through the ages, this...
-
From Frames to Pouring: The CRAM Cognitive Architecture for Everyday Robot Manipulation
The Cognitive Robot Abstract Machine (CRAM) was developed to enable robots to perform everyday manipulation tasks in human environments by transforming underspecified task instructions into context-sensitive, executable actions. Rather...
-
From Image Processing to Knowledge-based Video Generation at the University of Bremen 1993–2013
The research of the Image Processing group at the Mathematics/Computer Science Department of the University of Bremen was initially driven by requirements from the field of image retrieval, but it progressed very quickly to video and...
- The LILOG Project (1985–1991) by IBM Germany
- Explainable AI is far more than an Additional Technical Feature: A Conversation with Philipp A. Toussaint about Transparency, Trust, and the Future of Artificial Intelligence in Healthcare
-
Conceptual Orthospaces—An Embedding Framework Accounting for Negation Operators and Convexity Constraints
One aim of neurosymbolic AI is to enhance subsymbolic learning approaches with symbolic information, e.g., in the form of background knowledge, to increase result quality, interpretability, and trustworthiness. To model subsymbolic...
-
The Effects of Inhibitory Plasticity and the Emerging Network Dynamics on Processing Visual Information
Neurons along the visual pathway–from the retina to the primary visual cortex (V1) and higher visual areas–process information related to objects, such as their shape, texture, color, and direction of movement.The representation of...
-
Neuro-Symbolic Approaches for Class Expression Learning
This dissertation abstract is a summary of the published doctoral thesis "Fast Neuro-Symbolic Approaches for Class Expression Learning". The thesis focuses on the development of efficient methods for class expression learning on...
-
Abstraction and Explanation of Ontology-Driven Conceptual Models
Ontology-driven conceptual models are generally considered a distinct class of conceptual models, as they draw on the semantics of foundational ontologies to provide a strong basis for modeling elements. These models are designed as...
- Editorial: AI in the Energy Sector
- Can You Trust an LLM Even If You Prompted It Yourself?
-
Deep Reinforcement Learning for Price-Aware Building Heating Control
Abstract Heating systems account for a significant share of residential energy consumption, and rising energy prices call for intelligent, cost-aware control strategies. Traditional methods, such as rule-based or model predictive...
-
Long Term Wind Power Assessment based on Wind Speed Downscaling
Abstract Accurate assessment of long-term wind power potential requires high-resolution wind speed data, yet most climate projections operate at spatial resolutions too coarse for reliable local estimates. Deep learning methods...
-
ADVIS-G: An Adversarially Defended Intrusion Detection System for Smart Grids Using Deep Learning
Abstract Smart Grids (SG) enhance efficiency and centralised control by enabling networked device communication, but these capabilities expose them to cyberattacks. Machine Learning (ML) and Deep Learning (DL) based Intrusion Detection...