Auflistung nach Schlagwort "Explainable artificial intelligence"
1 - 3 von 3
Treffer pro Seite
Sortieroptionen
- ZeitschriftenartikelA Neural-Symbolic Approach for Explanation Generation Based on Sub-concept Detection: An Application of Metric Learning for Low-Time-Budget Labeling(KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Rabold, JohannesDeep learning methods, although effective in their assigned tasks, are mostly black-boxes with respect to their inner workings. For image classification with CNNs, there exists a variety of visual explanation methods that highlight parts of input images that were relevant for the classification result. But in many domains visual highlighting may not be expressive enough when the classification relies on complex relations within visual concepts. This paper presents an approach to enrich visual explanations with verbal local explanations, emphasizing important relational information. The proposed SymMetric algorithm combines metric learning and inductive logic programming (ILP). Labels given by a human for a small subset of important image parts are first generalized to a neighborhood of similar images using a learned distance metric. The information about labels and their spatial relations is then used to build background knowledge for ILP and ultimately to learn a first-order theory that locally explains the black-box with respect to the given image. The approach is evaluated with the Dogs vs. Cats data set demonstrating the generalization ability of metric learning and with Picasso Faces to illustrate recognition of spatial meaningful constellations of sub-concepts and creation of an expressive explanation.
- ZeitschriftenartikelIdentification of Explainable Structures in Data with a Human-in-the-Loop(KI - Künstliche Intelligenz: Vol. 36, No. 0, 2022) Thrun, Michael C.Explainable AIs (XAIs) often do not provide relevant or understandable explanations for a domain-specific human-in-the-loop (HIL). In addition, internally used metrics have biases that might not match existing structures in the data. The habilitation thesis presents an alternative solution approach by deriving explanations from high dimensional structures in the data rather than from predetermined classifications. Typically, the detection of such density- or distance-based structures in data has so far entailed the challenges of choosing appropriate algorithms and their parameters, which adds a considerable amount of complex decision-making options for the HIL. Central steps of the solution approach are a parameter-free methodology for the estimation and visualization of probability density functions (PDFs); followed by a hypothesis for selecting an appropriate distance metric independent of the data context in combination with projection-based clustering (PBC). PBC allows for subsequent interactive identification of separable structures in the data. Hence, the HIL does not need deep knowledge of the underlying algorithms to identify structures in data. The complete data-driven XAI approach involving the HIL is based on a decision tree guided by distance-based structures in data (DSD). This data-driven XAI shows initial success in the application to multivariate time series and non-sequential high-dimensional data. It generates meaningful and relevant explanations that are evaluated by Grice’s maxims.
- WorkshopbeitragThe Role of Explanations of AI Systems: Beyond Trust and Helping to Form Mental Models(Mensch und Computer 2021 - Workshopband, 2021) Norkute, MildaThis paper discusses research that explored different roles for explanations of AI systems. A lot of the research focuses on investigating the role of explanations in mediating the level of users’ trust in the AI system and helping them form correct mental models about it. This paper argues that more research should be dedicated to investigate the alternative roles that explanations could play in supporting the user’s interactions with AI systems such as helping them enrich the AI suggestions they are presented with or correct them, help users do tasks more efficiently and effectively.