Models that impact people’s lives must be honest and forthcoming about their doubts. This new method brings balance to explainable AI.

Left: images of celebrity faces in the CelebA dataset with predicted class label ‘no smile’. Right: pixels highlighted by our approach (red) that caused the model to be uncertain about that prediction. Images by author.

Uncertainty and Bayesian Deep Learning

Continue reading: https://towardsdatascience.com/how-to-make-artificial-intelligence-articulate-doubt-9c2885a9e541?source=rss—-7f60cf5620c9—4

Source: towardsdatascience.com