Professor CHRISTIAN WAGNER's Outputs (6)

Explain the world – Using causality to facilitate better rules for fuzzy systems (2024)
Journal Article
Zhang, T., Wagner, C., & Garibaldi, J. M. (2024). Explain the world – Using causality to facilitate better rules for fuzzy systems. IEEE Transactions on Fuzzy Systems, 1-14. https://doi.org/10.1109/TFUZZ.2024.3457962

The rules of a rule-based system provide explanations for its behaviour by revealing the relationships between the variables captured. However, ideally, we have AI systems which go beyond explainable AI (XAI), that is, systems which not only explain... Read More about Explain the world – Using causality to facilitate better rules for fuzzy systems.

Implementing responsible innovation: the role of the meso-level(s) between project and organisation (2024)
Journal Article
Stahl, B. C., Portillo, V., Wagner, H., Craigon, P. J., Darzentas, D., De Ossorno Garcia, S., Dowthwaite, L., Greenhalgh, C., Middleton, S. E., Nichele, E., Wagner, C., & Webb, H. (2024). Implementing responsible innovation: the role of the meso-level(s) between project and organisation. Journal of Responsible Innovation, 11(1), Article 2370934. https://doi.org/10.1080/23299460.2024.2370934

Much of academic discussion of responsible innovation (RI) has focused on RI integration into research projects. In addition, significant attention has also been paid to RI structures and policies at the research policy and institutional level. This... Read More about Implementing responsible innovation: the role of the meso-level(s) between project and organisation.

Generating Locally Relevant Explanations Using Causal Rule Discovery (2024)
Presentation / Conference Contribution
Zhang, T., & Wagner, C. (2024, June). Generating Locally Relevant Explanations Using Causal Rule Discovery. Presented at 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Yokohama, Japan

In the real-world an effect often arises via multiple causal mechanisms. Conversely, the behaviour of AI systems is commonly driven by correlations which may-or may not-be themselves linked to causal mechanisms in the associated real-world system the... Read More about Generating Locally Relevant Explanations Using Causal Rule Discovery.

Interval Agreement Weighted Average - Sensitivity to Data Set Features (2024)
Presentation / Conference Contribution
Zhao, Y., Wagner, C., Ryan, B., Pekaslan, D., & Navarro, J. (2024, June). Interval Agreement Weighted Average - Sensitivity to Data Set Features. Presented at 2024 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE), Yokohama, Japan

The growing use of intervals in fields like survey analysis necessitates effective aggregation methods that can summarize and represent such uncertain data representations. The Interval Agreement Approach (IAA) addresses this by aggregating interval... Read More about Interval Agreement Weighted Average - Sensitivity to Data Set Features.

SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME (2024)
Journal Article
Meng, H., Wagner, C., & Triguero, I. (2024). SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME. Neural Networks, 176, Article 106345. https://doi.org/10.1016/j.neunet.2024.106345

Local Interpretability Model-agnostic Explanations (LIME) is a well-known post-hoc technique for explaining black-box models. While very useful, recent research highlights challenges around the explanations generated. In particular, there is a potent... Read More about SEGAL time series classification — Stable explanations using a generative model and an adaptive weighting method for LIME.

Gradient-based Fuzzy System Optimisation via Automatic Differentiation – FuzzyR as a Use Case (2024)
Preprint / Working Paper
Chen, C., Wagner, C., & Garibaldi, J. M. (2024). Gradient-based Fuzzy System Optimisation via Automatic Differentiation – FuzzyR as a Use Case

Since their introduction, fuzzy sets and systems have become an important area of research known for its versatility in modelling, knowledge representation and reasoning, and increasingly its potential within the context explainable AI. While the app... Read More about Gradient-based Fuzzy System Optimisation via Automatic Differentiation – FuzzyR as a Use Case.