2 citations · 3 across the 5 of their papers we have counts for
5 papers
Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity
Tejas Pradeep Shirodkar, P. J. Narayanan
Singular learning theory characterises the complexity of a deep network through the geometry of its loss singularities. The local learning coefficient (LLC), the standard estimator…
Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale
Tejas Pradeep Shirodkar, P. J. Narayanan
Pretrained transformers sit near singular minima of the loss, where the Fisher information metric degenerates along dead directions: directions in parameter space along which the d…
Prototype Guided Backdoor Defense
Venkat Adithya Amula, Sunayana Samavedam, Saurabh Saini +2
Deep learning models are susceptible to {\em backdoor attacks} involving malicious attackers perturbing a small subset of training data with a {\em trigger} to causes misclassifica…
A survey on Concept-based Approaches For Model Improvement
Avani Gupta, P J Narayanan
The focus of recent research has shifted from merely improving the metrics based performance of Deep Neural Networks (DNNs) to DNNs which are more interpretable to humans. The fiel…
Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement
Avani Gupta, Saurabh Saini, P J Narayanan
Humans use abstract concepts for understanding instead of hard features. Recent interpretability research has focused on human-centered concept explanations of neural networks. Con…