Skip to main content
main-content

Zeitschrift

KI - Künstliche Intelligenz

German Journal on Artificial Intelligence - Organ des Fachbereichs "Künstliche Intelligenz" der Gesellschaft für Informatik e.V.

KI - Künstliche Intelligenz OnlineFirst articles

21.09.2017 | Research Project

Red Hen Lab: Dataset and Tools for Multimodal Human Communication Research

Researchers in the fields of AI and Communication both study human communication, but despite the opportunities for collaboration, they rarely interact. Red Hen Lab is dedicated to bringing them together for research on multimodal communication …

20.09.2017 | Interview

Cognition, Interaction, Design

Discussions as Part of the Codesign Roundtable 2017

This transcript documents select parts of discussions on the confluence of cognition, interaction, design, and human behaviour studies. The interview and related events were held as part of the CoDesign 2017 Roundtable (Bhatt in CoDesign 2017—The …

14.09.2017 | Doctoral and Postdoctoral Dissertations

Using Ontology-Based Data Access to Enable Context Recognition in the Presence of Incomplete Information

Ontologies play an important role as a semantic layer for data access in various areas such as the Semantic Web, medicine, and enterprise applications. They capture the terminology of an application domain and describe domain knowledge in a …

12.09.2017 | Technical Contribution

Assigning Group Activity Semantics to Multi-Device Mobile Sensor Data

An Explanation-Based Perspective

Numerous types of sensor data can be gathered via devices on mobile sensors, such as smartphones and smartwatches as well as things endowed with sensors. Such sensor data from disparate sources can be aggregated and inferences can be made about …

11.09.2017 | Doctoral and Postdoctoral Dissertations

Hierarchical Hybrid Planning for Mobile Robots

With the growing capabilities of robot hardware and software mobile robots are becoming more useful in real world environments. This makes reasoning about actions and their execution increasingly important if we want the robot to operate …

Aktuelle Ausgaben

Über diese Zeitschrift

The Scientific journal "KI – Künstliche Intelligenz" is the official journal of the division for artificial intelligence within the "Gesellschaft für Informatik e.V." (GI) – the German Informatics Society – with contributions from throughout the field of artificial intelligence. The journal presents all relevant aspects of artificial intelligence – the fundamentals and tools, their use and adaptation for scientific purposes, and applications which are implemented using AI methods – and thus provides the reader with the latest developments in and well-founded background information on all relevant aspects of artificial intelligence. For all members of the AI community the journal provides quick access to current topics in the field and promotes vital interdisciplinary interchange.

Preview:

Higher-Level Cognition and Computation

Human higher-level cognition is a multi-faceted and complex area of thinking which includes the mental processes of reasoning, decision making, creativity, and learning among others. Logic, understood as a normative theory of thinking, has a widespread and pervasive effect on the foundations of cognitive science. However, human reasoning cannot be completely described by logical systems. Sources of explanations are incomplete knowledge, incorrect beliefs, or inconsistencies. Still, humans have an impressive ability to derive satisficing, acceptable conclusions. Generally, people employ both inductive and deductive reasoning to arrive at beliefs; but the same argument that is inductively strong or powerful may be deductively invalid. Therefore, a wide range of reasoning mechanism has to be considered, such as analogical or defeasible reasoning.

The topics of interest include, but are not limited to:

• Analogical reasoning
Common sense and defeasible reasoning
Deductive calculi for higher-level cognition
• Inductive reasoning and cognition
• Preferred mental models and their formalization
• Probabilistic approaches of reasoning

The Künstliche Intelligenz journal, which is published and indexed by Springer, supports the following lists of formats: technical contributions, research projects, discussions, dissertation abstracts, conference reports and book reviews. If you are interested in contributing to this special issue, please contact one of the guest editors:

Dr. Marco Ragni
University of Freiburg
Center for Cognitive Science

Institute of Computer Science and Social Research
Friedrichstr. 50
D-79098 Freiburg, Germany
ragni@cognition.uni-freiburg.de
http://portal.uni-freiburg.de/cognition/members/ragni
Prof. Frieder Stolzenburg
Harz University of Applied Sciences
Automation & Computer Sciences Dep.
Friedrichstr. 57-59
38855 Wernigerode, Germany
fstolzenburg@hs-harz.de
fstolzenburg.hs-harz.de

Important dates:

• Statement of interest: 15-Aug-2014
• Submission deadline: 07-Oct-2014
• Notification: 15-Nov-2014
• Camera-ready copy: 15-Jan-2015
• Special issue: KI 3/2015

Submission and contribution format:

The articles should be written in english, in order to attract an international audience, formatted with the Springer LaTeX package for journals (\http://www.static.springer.com/sgw/documents/468198/application/zip/LaTeX.zip[).

Submissions should be sent as pdf file to fstolzenburg@hs-harz.de.

Advances in Autonomous Learning

Autonomous Learning research aims at understanding how adaptive systems can efficiently learn from the interaction with the environment, especially by having an integrated approach to decision making and learning, allowing systems to decide by themselves on actions, representations, hyper-parameters and model structures for the purpose of efficient learning.

It addresses challenges such as how to autonomously learn representations for efficient model use, how to arrive at suitable cost functions from meta-objectives (generalizing inverse RL), how to autonomously choose model structures and hyper-parameters in possibly non-stationary environments, or how to design efficient actor-reward strategies which generalize across tasks.

Application scenarios which require these type of complex models span high-impact domains such as robotics, life-long learning, intelligent tutoring, or big data analytics. We invite contributions related to the following non exhaustive list of topics:

– autonomous learning of rich data representations,
– active learning in structured (e.g., hybrid, relational) interactive domains,
– learning models with autonomous complexity adaptation,
– transfer learning,
– structure learning,
– statistical relational learning,
– theoretical advances to measure model autonomy,
– applications and project reports in the field of autonomous learning.

Prof. Barbara Hammer
Universität Bielefeld
D-33594 Bielefeld
Prof. Marc Toussaint

Universität Stuttgart
D-70569 Stuttgart

Companion Technologies

At present, we observe a rapid growth in the development of increasingly complex ‘‘intelligent’’ systems that serve users throughout all areas of their daily life. They range from classical technical systems such as household devices, cars, or consumer electronics through mobile apps and services to advanced service robots in various fields of application. While many of the rather conventional systems already provide multiple modalities to interact with, the most advanced are even equipped with cognitive abilities such as perception, cognition, and reasoning. However, the use of such complex technical systems and in particular the actual exploitation of their rich functionality remain challenging and quite often lead to users’ cognitive overload and frustration.

Companion Technologies aim at bridging the gap between the extensive functionality of technical systems and human users’ individual requirements and needs. They enable the construction of really smart—adaptive, flexible, and cooperative—technical systems by employing a combination of AI techniques and relying on psychological and neurobiological findings.

The special issue ‘‘Companion Technologies’’ of the KI Journal aims to present ongoing research, application perspectives, and other insights into an exciting research area emerging across the fields of Artificial Intelligence, Cognitive Psychology, and Cognitive Sciences. Topics of interest include, but are not limited to:
• Computational models of cognitive processes
• Reasoning for adaptive systems
• User-centered planning
• Multi-modal emotion and motivation recognition
• Knowledge-based human–computer interaction
• Knowledge-based dialogue management
• Cooperative and adaptive systems

The KI Journal, published and indexed by Springer, supports a variety of formats including technical articles, project descriptions, surveys, dissertation abstracts, conference reports, and book reviews.
Interested authors are asked to contact the guest editors at their earliest convenience:

Prof. Dr. Susanne Biundo-Stephan
Institute of Artificial Intelligence
Ulm University
89069 Ulm
susanne.biundo@uni-ulm.de

Daniel Höller
Institute of Artificial Intelligence
Ulm University
89069 Ulm
daniel.hoeller@uni-ulm.de

Pascal Bercher
Institute of Artificial Intelligence
Ulm University
89069 Ulm
pascal.bercher@uni-ulm.de

Weitere Informationen

Premium Partner

GI LogoNeuer Inhalt

BranchenIndex Online

Die B2B-Firmensuche für Industrie und Wirtschaft: Kostenfrei in Firmenprofilen nach Lieferanten, Herstellern, Dienstleistern und Händlern recherchieren.

Whitepaper

- ANZEIGE -

Erforderliche Schutzmaßnahmen für das (vernetzte) Auto

Längst sind moderne Autos kleine Rechnernetzwerke auf Rädern. Was bedeutet dies für die Sicherheit? Dieser Beitrag liefert einen Überblick über Angriffsmethoden und Sicherheitstechnologien für moderne Fahrzeuge. Jetzt gratis downloaden!