KI - Künstliche Intelligenz
Permanent URI for this communityhttps://dl.gi.de/handle/20.500.12116/11025
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.
Authors with most Documents
Browse
19 results
Search Results
Journal Article Digital Forensics AI: Evaluating, Standardizing and Optimizing Digital Evidence Mining Techniques(Springer, 2022) Solanke, Abiodun A.; Biasiotti, Maria AngelaThe impact of AI on numerous sectors of our society and its successes over the years indicate that it can assist in resolving a variety of complex digital forensics investigative problems. Forensics analysis can make use of machine learning models’ pattern detection and recognition capabilities to uncover hidden evidence in digital artifacts that would have been missed if conducted manually. Numerous works have proposed ways for applying AI to digital forensics; nevertheless, scepticism regarding the opacity of AI has impeded the domain’s adequate formalization and standardization. We present three critical instruments necessary for the development of sound machine-driven digital forensics methodologies in this paper. We cover various methods for evaluating, standardizing, and optimizing techniques applicable to artificial intelligence models used in digital forensics. Additionally, we describe several applications of these instruments in digital forensics, emphasizing their strengths and weaknesses that may be critical to the methods’ admissibility in a judicial process.Journal Article Evaluating Explainability Methods Intended for Multiple Stakeholders(Springer, 2021) Martin, Kyle; Liret, Anne; Wiratunga, Nirmalie; Owusu, Gilbert; Kern, MathiasExplanation mechanisms for intelligent systems are typically designed to respond to specific user needs, yet in practice these systems tend to have a wide variety of users. This can present a challenge to organisations looking to satisfy the explanation needs of different groups using an individual system. In this paper we present an explainability framework formed of a catalogue of explanation methods, and designed to integrate with a range of projects within a telecommunications organisation. Explainability methods are split into low-level explanations and high-level explanations for increasing levels of contextual support in their explanations. We motivate this framework using the specific case-study of explaining the conclusions of field network engineering experts to non-technical planning staff and evaluate our results using feedback from two distinct user groups; domain-expert telecommunication engineers and non-expert desk agent staff. We also present and investigate two metrics designed to model the quality of explanations - Meet-In-The-Middle (MITM) and Trust-Your-Neighbours (TYN). Our analysis of these metrics offers new insights into the use of similarity knowledge for the evaluation of explanations.Journal Article Learning by Enhancing Half-Baked AI Projects(Springer, 2021) Kahn, Ken; Winters, NiallWe have developed thirty sample artificial intelligence (AI) programs in a form suitable for enhancement by non-expert programmers. The projects are implemented in the Snap! blocks language and can be run in modern web browsers. These projects have been designed to be modifiable by school students and have been iteratively developed with over 100 students. The projects involve speech synthesis, speech and image recognition, natural language processing, and deep machine learning. They illustrate a variety of AI capabilities, concepts, and techniques. The intent is to provide students with hands-on experience with AI programming so they come to understand the possibilities, problems, strengths, and weaknesses of AI today.Journal Article Neural Network Construction Practices in Elementary School(Springer, 2021) Shamir, Gilad; Levin, IlyaThis paper describes an artificial intelligence (AI) educational project conducted with a small number of 12-year-old students. It is a preliminary step to add AI learning in a city-wide program consisting of elementary school students who learn computational thinking and digital literacy. Today children grow up in an age of AI which significantly affects how we live, work, and solve problems therefore AI should be taught in schools. Children usually employ AI models as black boxes without understanding the computational concepts, underlying assumptions, nor limitations of AI models. The hypothesis of this study is that to understand how machines learn, students should actively construct a neural network. To address this issue a dedicated curriculum and appropriate scaffolds were created for this study. It includes a programmable learning environment for elementary school students to construct AI agents. Findings show high engagement during the constructionist learning and that the novel learning environment helped make machine learning understandable.Journal Article How and What Can Humans Learn from Being in the Loop?(Springer, 2020) Abdel-Karim, Benjamin M.; Pfeuffer, Nicolas; Rohde, Gernot; Hinz, OliverThis article discusses the counterpart of interactive machine learning, i.e., human learning while being in the loop in a human-machine collaboration. For such cases we propose the use of a Contradiction Matrix to assess the overlap and the contradictions of human and machine predictions. We show in a small-scaled user study with experts in the area of pneumology (1) that machine-learning based systems can classify X-rays with respect to diseases with a meaningful accuracy, (2) humans partly use contradictions to reconsider their initial diagnosis, and (3) that this leads to a higher overlap between human and machine diagnoses at the end of the collaboration situation. We argue that disclosure of information on diagnosis uncertainty can be beneficial to make the human expert reconsider her or his initial assessment which may ultimately result in a deliberate agreement. In the light of the observations from our project, it becomes apparent that collaborative learning in such a human-in-the-loop scenario could lead to mutual benefits for both human learning and interactive machine learning. Bearing the differences in reasoning and learning processes of humans and intelligent systems in mind, we argue that interdisciplinary research teams have the best chances at tackling this undertaking and generating valuable insights.Journal Article Machine-Learning-Based Statistical Arbitrage Football Betting(Springer, 2020) Knoll, Julian; Stübinger, JohannesAcross countries and continents, football (soccer) has drawn increasingly more attention over the last decades and developed into a huge commercial complex. Consequently, the market of bookmakers providing the possibility to bet on the result of football matches grew rapidly, especially with the appearance of the internet. With a high number of games every week in multiple countries, football league matches hold enormous potential for generating profits over time with the use of advanced betting strategies. In this paper, we use machine learning for predicting the outcome of football league matches by exploiting data about match characteristics. Based on insights from the field of statistical arbitrage stock market trading, we show that one could generate meaningful profits over time by betting accordingly. A simulation study analyzing the matches of the five top European football leagues from season 2013/14 to 2017/18 presented economically and statistically significant returns achieved by exploiting large data sets with modern machine learning algorithms. In contrast to these modern algorithms, the break-even point could not be reached with an ordinary linear regression approach or simple betting strategies, e.g. always betting on the home team.Journal Article The CoRg Project: Cognitive Reasoning(Springer, 2019) Schon, Claudia; Siebert, Sophie; Stolzenburg, FriederThe term cognitive computing refers to new hardware and/or software that mimics the functioning of the human brain. In the context of question answering and commonsense reasoning this means that the reasoning process of humans shall be modeled by adequate technical means. However, since humans do not follow the rules of classical logic, a system designed to model these abilities must be very versatile. The aim of the CoRg project (Cognitive Reasoning) is to successfully complete a reasoning task with commonsense reasoning. We address different benchmarks with focus on the COPA benchmark set (Choice of Plausible Alternatives). Since humans naturally use background knowledge, we have to deal with large background knowledge bases and must be able to reason with multiple input formats and sources in the CoRg system, in order to draw explainable conclusions. For this, we have to find appropriate logics for cognitive reasoning. For a successful reasoning system, nowadays it seems to be important to combine automated reasoning with machine learning technology like recurrent neural networks.Journal Article Learning Inference Rules from Data(Springer, 2019) Sakama, Chiaki; Inoue, Katsumi; Ribeiro, TonyThis paper considers the possibility of designing AI that can learn logical or non-logical inference rules from data. We first provide an abstract framework for learning logics. In this framework, an agent $${{{\mathcal {A}}}}$$ A provides training examples that consist of formulas S and their logical consequences T . Then a machine $${{{\mathcal {M}}}}$$ M builds an axiomatic system that makes T a consequence of S . Alternatively, in the absence of an agent $$\mathcal{A}$$ A , a machine $${{{\mathcal {M}}}}$$ M seeks an unknown logic underlying given data. We next consider the problem of learning logical inference rules by induction. Given a set S of propositional formulas and their logical consequences T , the goal is to find deductive inference rules that produce T from S . We show that an induction algorithm LF1T , which learns logic programs from interpretation transitions, successfully produces deductive inference rules from input data. Finally, we consider the problem of learning non-logical inference rules. We address three case studies for learning abductive inference, frame axioms, and conversational implicature. Each case study uses machine learning techniques together with metalogic programming.Journal Article Multimodal Behavior Analytics for Interactive Technologies(Springer, 2016) Scherer, StefanJournal Article Learning Feedback in Intelligent Tutoring Systems(Springer, 2015) Gross, Sebastian; Mokbel, Bassam; Hammer, Barbara; Pinkwart, NielsIntelligent Tutoring Systems (ITSs) are adaptive learning systems that aim to support learners by providing one-on-one individualized instruction. Typically, instructing learners in ITSs is build on formalized domain knowledge and, thus, the applicability is restricted to well-defined domains where knowledge about the domain being taught can be explicitly modeled. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. As part of the DFG priority programme “Autonomous Learning”, the FIT project has been conducted over a period of 3 years pursuing the goal to develop novel ITS methods, that are also applicable for ill-defined problems, based on implicit domain knowledge extracted from educational data sets. Here, machine learning techniques have been used to autonomously infer structures from given learning data (e.g., student solutions) and, based on these structures, to develop strategies for instructing learners.