9 citations · 20 across the 9 of their papers we have counts for
6 papers · 1 filter
Dividing and Conquering a BlackBox to a Mixture of Interpretable Models: Route, Interpret, Repeat
Shantanu Ghosh, Ke Yu, Forough Arabshahi +1
ML model design either starts with an interpretable model or a Blackbox and explains it post hoc. Blackbox models are flexible but difficult to explain, while interpretable models…
Tackling Shortcut Learning in Deep Neural Networks: An Iterative Approach with Interpretable Models
Shantanu Ghosh, Ke Yu, Forough Arabshahi +1
We use concept-based interpretable models to mitigate shortcut learning. Existing methods lack interpretability. Beginning with a Blackbox, we iteratively carve out a mixture of in…
Augmentation by Counterfactual Explanation -- Fixing an Overconfident Classifier
Sumedha Singla, Nihal Murali, Forough Arabshahi +2
A highly accurate but overconfident model is ill-suited for deployment in critical applications such as healthcare and autonomous driving. The classification outcome should reflect…
Compositional Generalization with Tree Stack Memory Units
Forough Arabshahi, Zhichu Lu, Pranay Mundra +2
We study compositional generalization, viz., the problem of zero-shot generalization to novel compositions of concepts in a domain. Standard neural networks fail to a large extent…
Combining Symbolic Expressions and Black-box Function Evaluations in Neural Programs
Forough Arabshahi, Sameer Singh, Animashree Anandkumar
Neural programming involves training neural networks to learn programs, mathematics, or logic from data. Previous works have failed to achieve good generalization performance, espe…
Spectral Methods for Correlated Topic Models
Forough Arabshahi, Animashree Anandkumar
In this paper, we propose guaranteed spectral methods for learning a broad range of topic models, which generalize the popular Latent Dirichlet Allocation (LDA). We overcome the li…