DeepSeer: Interactive RNN Explanation and Debugging via State Abstraction

Wang, Zhijie; Huang, Yuheng; Song, Da; Ма, Лей; Zhang, Tianyi

doi:10.1145/3544548.3580852

Search citation statements

Order By: Relevance

Paper Sections

Select...

Discussion 61 Combining Different Types Of Explanations For ...1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Other2

Article1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, our qualitative study participants expressed a need for local explanations. A fusion of global and local explanations can be most useful for domain experts as local explanations provide a better contextualisation of global explanations [81], which we believe is essential for successful model steering. For example, local data-centric explanations can bolster the validity of the top decision rules by allowing users to access specific records that fulfil the rule.…”

Section: Discussion 61 Combining Different Types Of Explanations For ...mentioning

confidence: 99%

EXMOS: Explanatory Model Steering through Multifaceted Explanations and Data Configurations

Bhattacharya,

Stumpf,

Gosak

et al. 2024

Proceedings of the CHI Conference on Human Factors in Computing Systems

View full text Add to dashboard Cite

Figure 1: Explanatory Model Steering (EXMOS) enable users to fine-tune prediction models with the help of Explainable AI and Interactive Machine Learning. This research explores the influence of different types of global explanations for supporting domain experts, such as healthcare experts, in improving ML models through manual and automated data configurations. The refined prediction model also dynamically updates the explanations and the predicted outcomes.

show abstract

Section: Discussion 61 Combining Different Types Of Explanations For ...mentioning

confidence: 99%