Concept bottleneck models (CBM) are a popular way of creating more interpretable neural
networks by having hidden layer neurons correspond to human-understandable concepts …

We observe that the mapping between an image's representation in one model to its
representation in another can be learned surprisingly well with just a linear layer, even …

Abstract Deep Neural Networks (DNNs) demonstrated remarkable capabilities in learning
complex hierarchical data representations, but the nature of these representations remains …

Labeling neural network submodules with human-legible descriptions is useful for many
downstream tasks: such descriptions can surface failures, guide interventions, and perhaps …

The demand for transparency in healthcare and finance has led to interpretable machine
learning (IML) models, notably the concept bottleneck models (CBMs), valued for their …

Compositional Explanations is a method for identifying logical formulas of concepts that
approximate the neurons' behavior. However, these explanations are linked to the small …

The field of explainable artificial intelligence emerged in response to the growing need for
more transparent and reliable models. However, using raw features to provide explanations …

Abstract Information Pursuit (IP) is a classical active testing algorithm for predicting an output
by sequentially and greedily querying the input in order of information gain. However, IP is …

How does the internal computation of a machine learning model transform inputs into
predictions? In this paper, we introduce a task called component modeling that aims to …

Abstract Concept activation vectors (CAVs) enable interpretability of a model with respect to
human concepts, though CAV generation requires the costly step of curating positive and …