Reviews 1 — Mara Graziani

Uncovering Unique Concept Vectors through Latent Space Decomposition

— Preprint — ICLR 2023 Workshops — Repo — Pypi

A global taxonomy of interpretable AI: Unifying the terminology for the technical and social sciences

— AI Review 56 —Global Taxonomy Meeting Recording — Global Taxonomy Initiative — Slides

Disentangling Neuron Representations with Concept Vectors

— CVPR 2023 Workshops — Medium post — Repo

Learning interpretable Microscopic Features of Tumor by Multi-task Adversarial CNNs to Improve Generalization

— Machine Learning for Biomedical Imaging Journal 2 — Repo

Attention-based Interpretable Regression of Gene Expression in Histology

— iMIMIC at MICCAI2022 — Extension paper preprint