South America
The Dollar Street Dataset: Images Representing the Geographic and Socioeconomic Diversity of the World
This dataset includes images from homes with no internet access and incomes as low as $26.99 per
Interaction-Grounded Learning with Action-Inclusive Feedback
Prior analyzed approaches fail when the feedback vector contains the action, which significantly limits IGL's success in many potential scenarios such as Brain-computer interface (BCI) or Human-computer interface (HCI) applications.
Interaction-Grounded Learning with Action-Inclusive Feedback
Prior analyzed approaches fail when the feedback vector contains the action, which significantly limits IGL's success in many potential scenarios such as Brain-computer interface (BCI) or Human-computer interface (HCI) applications.
618faa1728eb2ef6e3733645273ab145-Paper.pdf
It is hard to trust a black-box algorithm, and it is hard to deploy an algorithm if one does not trust its output.
Foundations of Symbolic Languages for Model Interpretability Marcelo Arenas 1,4, Daniel Baez
Several queries and scores have been proposed to explain individual predictions made by ML models. Examples include queries based on "anchors", which are parts of an instance that are sufficient to justify its classification, and "feature-perturbation" scores such as SHAP .
Decision Trees with Short Explainable Rules
Machine learning models and algorithms appear more and more frequently in systems that make decisions with an impact in our lives.