Artificial Smarts
AI often produces results without explaining why those decisions are correct.
And these insights could allow the user to decide whether a model is ready to be deployed.
Shared Interest works by comparing saliency methods to human-generated annotations.
KanawatTH / Getty Images
Shared Interest enabled the dermatologist to quickly see examples of the models correct and incorrect predictions.
The reasoning behind a models decision is important to both machine learning researcher and the decision-maker.
The reasoning behind a models decision is important to both machine learning researcher and the decision-maker, Hagag said.
metamorworks / Getty Images
But, said Buteneers, AI still makes some mistakes that humans never would.
