Logo des Repositoriums

Auflistung nach Autor:in "Stolzenburg, Frieder"

1 - 10 von 19
  • Textdokument
    Adapting Natural Language Processing Strategies for Stock Price Prediction
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Voigt, Frederic
    Due to the parallels between Natural Language Processing (NLP) and stock price prediction (SPP) as a time series problem, an attempt is made to interpret SPP as an NLP problem. As adaptable techniques word vector representations, pre-trained language models, advanced recurrent neural networks, unsupervised learning methods, and multimodal methods are introduced and it is outlined how they can be transferred into the stock prediction domain.
  • Textdokument
    Automatic German Easy Language (Leichte Sprache) Simplification: Data, Requirements and Approaches
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Schomacker, Thorben
    With the rise of the internet, it has become convenient and often free to access an abundance of texts. However, not all people, who have access, can really read and understand the texts. Despite the fact that, they speak the language that the text is written in. Most often this problem originates in the too complex nature of the texts. Text Simplification can help to overcome this barrier. In my dissertation, I want to specially focus on Leichte Sprache (German Easy Language). Which is a simplified version of German, that is tailored to the needs of people with cognitive disabilities.
  • Zeitschriftenartikel
    Cognitive Reasoning: A Personal View
    (KI - Künstliche Intelligenz: Vol. 33, No. 3, 2019) Furbach, Ulrich; Hölldobler, Steffen; Ragni, Marco; Schon, Claudia; Stolzenburg, Frieder
    The adjective cognitive especially in conjunction with the word computing seems to be a trendy buzzword in the artificial intelligence community and beyond nowadays. However, the term is often used without explicit definition. Therefore we start with a brief review of the notion and define what we mean by cognitive reasoning . It shall refer to modeling the human ability to draw meaningful conclusions despite incomplete and inconsistent knowledge involving among others the representation of knowledge where all processes from the acquisition and update of knowledge to the derivation of conclusions must be implementable and executable on appropriate hardware. We briefly introduce relevant approaches and methods from cognitive modeling, commonsense reasoning, and subsymbolic approaches. Furthermore, challenges and important research questions are stated, e.g., developing a computational model that can compete with a (human) reasoner on problems that require common sense.
  • Textdokument
    Continuous Image Classification on Data Streams using Contrastive Learning and Cluster Analysis
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Schliebitz, Andreas
    This PhD proposal presents a concept for an AI-based computer vision system trained on image data streams for real-time classification of unlabeled objects. The required AI models are trained through an underexplored combination of self-supervised and incremental learning. Emphasis will be placed on contrastive learning using the SimCLR framework and its successors. The need for such a system is motivated by the observation that supervised learning approaches often require large labeled datasets. The labeling process, which is usually performed manually, is not only time-consuming but inherently prone to errors. For sufficiently large image data streams, timely labeling of samples becomes impossible leading to sporadic data annotation cycles and the capture of only temporarily representative features. Such an approach might also render the resulting classifier vulnerable to domain shift and concept drift. The image data stream used in this proposal consists of unlabeled color images of clean potatoes, which are to be sorted into several defect classes by a self-supervised classifier. Contrastive transfer learning is performed on this image data stream for the selection of a feature extractor. In this approach, different pre-trained backbone architectures are adapted and evaluated using the SimCLR framework. The classifiers are evaluated based on their generated feature vectors using cluster analysis. This involves searching for novel evaluation methods that do not require labels and are more suitable for judging model performance than existing methods. Furthermore, by clustering the feature vectors, an automatic and adaptive classification might be achievable without the use of labels. In a subsequent step, the self-supervised classifiers are continuously improved using incremental learning methods. For this the models are incrementally trained on the image data stream over a longer period of time. Potential adjustments to the data stream could increase the classifier’s accuracy as well as make it more robust to domain adaptation problems. A final validation of the incrementally self-learning classification system can be performed with smaller, manually annotated datasets.
  • Konferenzbeitrag
    Entwicklung interdisziplinärer Module in der Hochschulbildung
    (INFORMATIK 2023 - Designing Futures: Zukünfte gestalten, 2023) Krause, Stefanie; Adler, Simon; Bühl, Johannes; Schenkendorf, René; Schneider, Kerstin; Stolzenburg, Frieder; Transchel, Fabian
    Um der zunehmenden Bedeutung der künstlichen Intelligenz (KI) für Unternehmen Rechnung zu tragen, entwickelt die Hochschule Harz interdisziplinäre Module im Rahmen des kooperativen Studiengangs AI Engineering – Künstliche Intelligenz in den Ingenieurwissenschaften, unter anderem in den Bereichen Mobile Systeme und Telematik. Im vorliegenden Beitrag wird ein Einblick in die geplante Umsetzung für ausgewählte Module gegeben.
  • Textdokument
    Evaluating Dangerous Capabilities of Large Language Models: An Examination of Situational Awareness
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Yadav, Dipendra
    The focal point of this research proposal pertains to a thorough examination of the inherent risks and potential challenges associated with the use of Large Language Models (LLMs). Emphasis has been laid on the facet of situational awareness, an attribute signifying a model’s understanding of its environment, its own state, and the implications of its actions. The proposed research aims to design a robust and reliable metric system and a methodology to gauge situational awareness, followed by an in-depth analysis of major LLMs using this developed metric. The intention is to pinpoint any latent hazards and suggest effective strategies to mitigate these issues, with the ultimate goal of promoting the responsible and secure advancement of artificial intelligence technologies.
  • Textdokument
    Exploring Adversarial Transferability in Real-World Scenarios: Understanding and Mitigating Security Risks
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Shrestha, Abhishek
    Deep Neural Networks (DNNs) are known to be vulnerable to artificially generated samples known as adversarial examples. Such adversarial samples aim at generating misclassifications by specifically optimizing input data for a matching perturbation. Interestingly, it can be observed that these adversarial examples are transferable from the source network where they were created to a black-box target network. The transferability property means that attackers are no longer required to have white-box access to models nor bound to query the target model repeatedly to craft an effective attack. Given the rising popularity of the use of DNNs in various domains, it is crucial to understand the vulnerability of these networks to such attacks. In this premise, the thesis intends to study transferability under a more realistic scenario, where source and target models can differ in various aspects like accuracy, capacity, bitwidth, and architecture among others. Furthermore, the goal is to also investigate defensive strategies that can be utilized to minimize the effectiveness of these attacks.
  • Zeitschriftenartikel
    Higher-Level Cognition and Computation: A Survey
    (KI - Künstliche Intelligenz: Vol. 29, No. 3, 2015) Ragni, Marco; Stolzenburg, Frieder
    Higher-level cognition is one of the constituents of our human mental abilities and subsumes reasoning, planning, language understanding and processing, and problem solving. A deeper understanding can lead to core insights to human cognition and to improve cognitive systems. There is, however, so far no unique characterization of the processes of human cognition. This survey introduces different approaches from cognitive architectures, artificial neural networks, and Bayesian modeling from a modeling perspective to vibrant fields such as connecting neurobiological processes with computational processes of reasoning, frameworks of rationality, and non-monotonic logics and common-sense reasoning. The survey ends with a set of five core challenges and open questions relevant for future research.
  • Textdokument
    Learning the Generation of Balanced Game Levels
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Rupp, Florian
    Games, including board games and video games, are widely popular and serve as a platform for entertainment while also challenging various cognitive abilities. A game, especially if it’s a competitive multiplayer setting, needs to be balanced in order to provide a joyful experience for all players. The balancing process of such game levels, however, requires a lot of work and manual testing. To address this shortcoming, this thesis aims to implement methods to automatically generate balanced game levels. Therefore, four research questions with ideas for problem-solving approaches are presented: (1) the development and evaluation of metrics to measure the balancing state of a game, (2) research on methods for learning the procedural generation of balanced levels, (3) balance levels for players with different strategies and, (4) examine how findings can be applied to other research areas. Methods from the field of procedural content generation, especially in combination with machine learning methods, are promising to answer these questions. In a first paper, I already introduced a reinforcement learning based approach to create balanced levels for two players.
  • Textdokument
    Lightweight Federated Learning Based Detection of Malicious Activity in Distributed Networks
    (DC@KI2023: Proceedings of Doctoral Consortium at KI 2023, 2023) Wöhnert, Kai Hendrik
    In an increasingly complex cyber threat landscape, traditional malware detection methods often fall short, particularly within resource-limited distributed networks like smart grids. This research project aims to develop an efficient malware detection system for such distributed networks, focusing on three elements: feature extraction, feature selection, and classification. For classification, a lightweight and accurate machine-learning model needs to be developed.