Zobrazeno 1 - 9
of 9
pro vyhledávání: '"Rahnama, Amir Hossein Akhavan"'
The number of local model-agnostic explanation techniques proposed has grown rapidly recently. One main reason is that the bar for developing new explainability techniques is low due to the lack of optimal evaluation measures. Without rigorous measur
Externí odkaz:
http://arxiv.org/abs/2310.03466
Local explanations of learning-to-rank (LTR) models are thought to extract the most important features that contribute to the ranking predicted by the LTR model for a single data point. Evaluating the accuracy of such explanations is challenging sinc
Externí odkaz:
http://arxiv.org/abs/2203.02295
Evaluating explanation techniques using human subjects is costly, time-consuming and can lead to subjectivity in the assessments. To evaluate the accuracy of local explanations, we require access to the true feature importance scores for a given inst
Externí odkaz:
http://arxiv.org/abs/2106.02488
LIME is a popular approach for explaining a black-box prediction through an interpretable model that is trained on instances in the vicinity of the predicted instance. To generate these instances, LIME randomly selects a subset of the non-zero featur
Externí odkaz:
http://arxiv.org/abs/1910.14421
Publikováno v:
The Journal of Supercomputing (2018)
In order to find hyperparameters for a machine learning model, algorithms such as grid search or random search are used over the space of possible values of the models hyperparameters. These search algorithms opt the solution that minimizes a specifi
Externí odkaz:
http://arxiv.org/abs/1803.10927
Publikováno v:
IEEE 2014 International Conference on Control, Decision and Information Technologies (CoDIT)
Big data trend has enforced the data-centric systems to have continuous fast data streams. In recent years, real-time analytics on stream data has formed into a new research field, which aims to answer queries about what-is-happening-now with a negli
Externí odkaz:
http://arxiv.org/abs/1612.08543
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
Data Mining & Knowledge Discovery; Jan2024, Vol. 38 Issue 1, p237-280, 44p
Publikováno v:
2014 International Conference on Control, Decision & Information Technologies (CoDIT); 2014, p789-794, 6p