Please register on Eventbrite:
https://www.eventbrite.ca/e/glocalx-from-local-to-global-explanations-of-black-box-ai-models-tickets-153390387779
Accurate AI models often are black-boxes which we are not able to understand. Applications in sensitive and critical domains are a strong motivational factor in trying to understand the behavior of black-boxes. In this study authors proposed to address this issue by providing an interpretable layer on top of black-box models by aggregating “local” explanations. GLocalX iteratively generalizes them into global explanations by hierarchically aggregating them.
For more information, visit https://ai.science
For any questions, email hello@ai.science
Join our slack community for free:
https://join.slack.com/t/aisc-to/shared_invite/zt-f5zq5l35-PSIJTFk4v60FML177PgsPg