5 papers
Dynamic Mode Decomposition along Depth in Vision Transformers
Nishant Suresh Aswani, Saif Eddin Jabari
Recent work has shown that contiguous vision transformer (ViT) blocks (a) can be replaced by a linear map and (b) organize into recurrent phases of computation. We ask whether thes…
Koopman Autoencoders Learn Neural Representation Dynamics
Nishant Suresh Aswani, Saif Eddin Jabari
This paper explores a simple question: can we model the internal transformations of a neural network using dynamical systems theory? We introduce Koopman autoencoders to capture ho…
Representing Neural Network Layers as Linear Operations via Koopman Operator Theory
Nishant Suresh Aswani, Saif Eddin Jabari, Muhammad Shafique
The strong performance of simple neural networks is often attributed to their nonlinear activations. However, a linear view of neural networks makes understanding and controlling n…
Exploring the Interplay of Interpretability and Robustness in Deep Neural Networks: A Saliency-guided Approach
Amira Guesmi, Nishant Suresh Aswani, Muhammad Shafique
Adversarial attacks pose a significant challenge to deploying deep learning models in safety-critical applications. Maintaining model robustness while ensuring interpretability is…
Examining Changes in Internal Representations of Continual Learning Models Through Tensor Decomposition
Nishant Suresh Aswani, Amira Guesmi, Muhammad Abdullah Hanif +1
Continual learning (CL) has spurred the development of several methods aimed at consolidating previous knowledge across sequential learning. Yet, the evaluations of these methods h…