5 papers
Interactive Concept Bottleneck Models
Kushal Chauhan, Rishabh Tiwari, Jan Freyberg +2
Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the…
Shaken, and Stirred: Long-Range Dependencies Enable Robust Outlier Detection with PixelCNN++
Barath Mohan Umapathi, Kushal Chauhan, Pradeep Shenoy +1
Reliable outlier detection is critical for real-world deployment of deep learning models. Although extensively studied, likelihoods produced by deep generative models have been lar…
Matching options to tasks using Option-Indexed Hierarchical Reinforcement Learning
Kushal Chauhan, Soumya Chatterjee, Akash Reddy +2
The options framework in Hierarchical Reinforcement Learning breaks down overall goals into a combination of options or simpler tasks and associated policies, allowing for abstract…
Robust outlier detection by de-biasing VAE likelihoods
Kushal Chauhan, Barath Mohan U, Pradeep Shenoy +2
Deep networks often make confident, yet, incorrect, predictions when tested with outlier data that is far removed from their training distributions. Likelihoods computed by deep ge…
Improving Segmentation for Technical Support Problems
Kushal Chauhan, Abhirut Gupta
Technical support problems are often long and complex. They typically contain user descriptions of the problem, the setup, and steps for attempted resolution. Often they also conta…