Kathryn Morse
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kathryn Morse has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chenglin Miao
Iowa State University
2 shared publications - Mengdi Huai
Iowa State University
2 shared publications - Aobo Chen
Department of Computer Science Iowa State University
1 shared publication Bridget Sullivan
Iowa State University
1 shared publication- Divya Lidder
Iowa State University
1 shared publication Wei Qian
Iowa State University
1 shared publication
Latest Publications
- Open Access
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (28) , 29412-29414
Neuron Explanations for Conformal Prediction (Student Abstract)
Conformal prediction (CP) has gained prominence as a popular technique for uncertainty quantification in deep neural networks (DNNs), providing statistically rigorous uncertainty sets. However, existing CP methods fail to clarify the origins of predictive uncertainties. While neuron-level interpretability has been effective in revealing the internal mechanisms of DNNs, explaining CP at the neuron level remains unexplored. Nonetheless, generating neuron explanations for CP is challenging due to the discrete and non-differentiable characteristics of CP, and the labor-intensive process of semantic annotation. To address these limitations, this paper proposes a novel neuron explanation approach for CP by identifying neurons crucial for understanding predictive uncertainties and automatically generating semantic explanations. The effectiveness of the proposed method is validated through both qualitative and quantitative experiments.
- 11 April 2025
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 39 (28) , 29412-29414
Open AccessNeuron Explanations for Conformal Prediction (Student Abstract)
Conformal prediction (CP) has gained prominence as a popular technique for uncertainty quantification in deep neural networks (DNNs), providing statistically rigorous uncertainty sets. However, existing CP methods fail to clarify the origins of predictive uncertainties. While neuron-level interpretability has been effective in revealing the internal mechanisms of DNNs, explaining CP at the neuron level remains unexplored. Nonetheless, generating neuron explanations for CP is challenging due to the discrete and non-differentiable characteristics of CP, and the labor-intensive process of semantic annotation. To address these limitations, this paper proposes a novel neuron explanation approach for CP by identifying neurons crucial for understanding predictive uncertainties and automatically generating semantic explanations. The effectiveness of the proposed method is validated through both qualitative and quantitative experiments.
- 3 October 2024
- Published by Springer Nature
- p. 557-567
Modeling and Understanding Uncertainty in Medical Image Classification
- 3 October 2024
- Published by Springer Nature
- p. 557-567
Modeling and Understanding Uncertainty in Medical Image Classification