Logo des Repositoriums

Auflistung nach Autor:in "Hammer, Barbara"

1 - 7 von 7
  • Zeitschriftenartikel
    Agnostic Explanation of Model Change based on Feature Importance
    (KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Muschalik, Maximilian; Fumagalli, Fabian; Hammer, Barbara; Hüllermeier, Eyke
    Explainable Artificial Intelligence (XAI) has mainly focused on static learning tasks so far. In this paper, we consider XAI in the context of online learning in dynamic environments, such as learning from real-time data streams, where models are learned incrementally and continuously adapted over the course of time. More specifically, we motivate the problem of explaining model change , i.e. explaining the difference between models before and after adaptation, instead of the models themselves. In this regard, we provide the first efficient model-agnostic approach to dynamically detecting, quantifying, and explaining significant model changes. Our approach is based on an adaptation of the well-known Permutation Feature Importance (PFI) measure. It includes two hyperparameters that control the sensitivity and directly influence explanation frequency, so that a human user can adjust the method to individual requirements and application needs. We assess and validate our method’s efficacy on illustrative synthetic data streams with three popular model classes.
  • Zeitschriftenartikel
    Autonomous Learning of Representations
    (KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Walter, Oliver; Haeb-Umbach, Reinhold; Mokbel, Bassam; Paassen, Benjamin; Hammer, Barbara
    Besides the core learning algorithm itself, one major question in machine learning is how to best encode given training data such that the learning technology can efficiently learn based thereon and generalize to novel data. While classical approaches often rely on a hand coded data representation, the topic of autonomous representation or feature learning plays a major role in modern learning architectures. The goal of this contribution is to give an overview about different principles of autonomous feature learning, and to exemplify two principles based on two recent examples: autonomous metric learning for sequences, and autonomous learning of a deep representation for spoken language, respectively.
  • Zeitschriftenartikel
    Challenges in Neural Computation
    (KI - Künstliche Intelligenz: Vol. 26, No. 4, 2012) Hammer, Barbara
    This contribution contains a short history of neural computation and an overview about the major learning paradigms and neural architectures used today.
  • Konferenzbeitrag
    Feedback provision strategies in intelligent tutoring systems based on clustered solution spaces
    (DeLFI 2012: Die 10. e-Learning Fachtagung Informatik der Gesellschaft für Informatik e.V., 2012) Gross, Sebastian; Mokbel, Bassam; Hammer, Barbara; Pinkwart, Niels
    Designing an Intelligent Tutoring System (ITS) usually requires precise models of the underlying domain, as well as of how a human tutor would respond to student mistakes. As such, the applicability of ITSs is typically restricted to welldefined domains where such a formalization is possible. The extension of ITSs to ill-defined domains constitutes a challenge. In this paper, we propose the provision of feedback based on solution spaces which are automatically clustered by machine learning techniques operating on sets of student solutions. We validated our approach in an expert evaluation with a data set from a programming course. The evaluation confirmed the feasibility of the proposed feedback provision strategies.
  • Zeitschriftenartikel
    Learning Feedback in Intelligent Tutoring Systems
    (KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Gross, Sebastian; Mokbel, Bassam; Hammer, Barbara; Pinkwart, Niels
    Intelligent 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.
  • Zeitschriftenartikel
    Special Issue on Autonomous Learning
    (KI - Künstliche Intelligenz: Vol. 29, No. 4, 2015) Hammer, Barbara; Toussaint, Marc
  • Zeitschriftenartikel
    Special Issue on Neural Learning Paradigms
    (KI - Künstliche Intelligenz: Vol. 26, No. 4, 2012) Hammer, Barbara