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.
Artificial Intelligence in Games, Vol. 34, Issue 1
The special issue focuses on artificial intelligence (AI) methods applied in and for different types of games (e.g., board games, video games, serious games). Games have been shown to be the perfect testbed for advanced AI methods. AI in games is now a well established research area with two dedicated conferences and as well as a dedicated journal. Especially deep learning methods have recently proven to beat the best human experts in Atari video games and the game Go. Other methods such as evolutionary computation have been shown to allow complete new types of games through procedural content generation. While there has been much progress in game AI recently, some games such as StarCraft remain beyond even the most advanced AI algorithms. The goal of this special issue is to present a survey of the current research in Game AI and emerging trends in this area.
Challenges in Interactive Machine Learning, Vol. 34, Issue 2
Designing successful interactive learning schemes requires to solve a number of key challenges like minimizing the cognitive cost for the user while optimizing query informativeness, devising effective interaction protocols based on different types of queries (membership, ranking, search, explanation, etc.), producing optimal questions by explicitly and efficiently capturing the uncertainty of the model, distributing the load of query answering across multiple teachers with heterogeneous abilities, designing or estimating realistic models of user behavior, increasing tolerance to noise and actively guiding the user toward providing better and more robust supervision, and, more generally, automatically discovering the user's expertise level and adapting the interaction accordingly. Such an interaction is likely to help make such systems more transparent and the results more explainable. Only then interactive learning will unlock unprecedented opportunities for both scientific research and commercial exploitation in Artificial Intelligence, Health Care, Environment and Climate, Physics and Astronomy, Chemistry, Bioinformatics, Agriculture, Social Web, Finance, e-Commerce, and Design, among other domains. This special issue aims at surveying established research in interactive learning, as well as overviewing recent advances on algorithms, models and effective process design around humans in the loop.
Ontologies and Data Management, Vol. 34, Issue 3
This special issue focuses on the theory and practice of applying ontologies in data management (ODM), which is a research topic of significant interest in Knowledge Representation and Reasoning (KR&R) and Database Theory. Modern data-centric software systems need to handle data that is often heterogeneous, sensitive, very large, and even incomplete or inconsistent. Moreover, it often has very complex structures. Thus, the development of proper tools and techniques to handle this complexity is a pressing task. Ontologies in combination with automated reasoning are acknowledged as a promising tool to address some of these challenges, and thus are receiving significant attention both among researchers and industry. For instance, the prominent data integration paradigm called ontology-based data access (OBDA) suggests the use of ontologies to provide a conceptual view of a problem domain, where various possibly heterogeneous data sources can be linked to the same ontology using mappings, enabling users to pose queries using the ontology vocabulary. For query answering in OBDA, automated reasoning is used to compile information from the sources, possibly employing the domain knowledge in the ontology to infer new information.
Developmental Robotics, Vol. 34, Issue 4
Human intelligence develops through experience, robot intelligence is engineered -- is it? At least in the mainstream approaches based on classical Artificial Intelligence (AI) and Machine Learning (ML) the robotic engineering approach is pursued and data- or knowledge-based algorithms are designed to improve a robot's problem-solving performance. Based on this engineering perspective of classical AI/ML approaches plenty of valuable applicationspecific impact has been achieved. Yet, the achievements are often subject to restrictions that involve domain knowledge as well as constraints concerning application domains and computational hardware. Developmental Robotics seeks to extend this constrained perspective of engineered artificial robotic cognition, by building on inspiration from biological developmental processes to design robots that learn in an open-ended continuous fashion. Developmental Robotics considers cognitive domains that involve problem-solving, self-perception, developmental disorders and embodied cognition. This perspective helps to improve the performance of intelligent robotic agents, and it has already led to significant contributions that inspired cutting-edge application-oriented Machine Learning technology. In addition, Developmental Robotics also provides functional computational models that help to understand and to investigate embodied cognitive processes.
- Daniel Sonntag
- Publishing model
- Hybrid. Open Access options available
- 88 days
- Submission to first decision
- 148 days
- Submission to acceptance
- 62,491 (2018)