5 citations · 9 across the 4 of their papers we have counts for
4 papers
From slides (through tiles) to pixels: an explainability framework for weakly supervised models in pre-clinical pathology
Marco Bertolini, Van-Khoa Le, Jake Pencharz +4
In pre-clinical pathology, there is a paradox between the abundance of raw data (whole slide images from many organs of many individual animals) and the lack of pixel-level slide a…
Explaining, Evaluating and Enhancing Neural Networks' Learned Representations
Marco Bertolini, Djork-Arné Clevert, Floriane Montanari
Most efforts in interpretability in deep learning have focused on (1) extracting explanations of a specific downstream task in relation to the input features and (2) imposing const…
Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
Ryan Henderson, Djork-Arné Clevert, Floriane Montanari
Rationalizing which parts of a molecule drive the predictions of a molecular graph convolutional neural network (GCNN) can be difficult. To help, we propose two simple regularizati…
Gini in a Bottleneck: Sparse Molecular Representations for Graph Convolutional Neural Networks
Ryan Henderson, Djork-Arné Clevert, Floriane Montanari
Due to the nature of deep learning approaches, it is inherently difficult to understand which aspects of a molecular graph drive the predictions of the network. As a mitigation str…