iSee collaborate with Mexico group AAAIMX, on a use case around nature event prediction and explaining these predictions. The data manipulated by the classifiers (core of prediction here) are mainly images. We thus need to find explanation methods that work on image classification tasks.
University of Madrid (UCM) has been working on the use case to identify explanation methods suitable for this goal. The paper accepted at International Case-base-reasoning conference ICCBR 2021 talks about “A case-based approach for the selection of explanation algorithms in image classification.”
interested in more details ? reach out to Juan Recio-Garcia (UCM)
Authors: (UCM) Juan Recio-Garcia, (AAAIMX) Humberto Parejas-Llanovarced, Mauricio Orozco-del-castillo, or Esteban Brito-Borges.