Regular biography
Vikram Ramaswamy is a Lecturer in the Department of Computer Science at Princeton University. He joined the department in 2023 after completing a Ph.D. at Princeton University and obtaining bachelor's and master's degrees at IIT Madras in India. His research interests include fairness and interpretability in machine learning, with a focus on their application to visual systems. Ramaswamy has worked primarily on constructing better datasets, both real and synthetic, and on understanding and evaluating interpretability methods for convolutional neural networks.
Scholar-generated biography
Vikram V. Ramaswamy is a researcher at Princeton University with expertise in Computer Vision, Fairness in AI, and Explainable AI. His work focuses on addressing biases in machine learning systems, particularly in visual datasets and models. He explores methods to enhance fairness, such as latent space de-biasing and intersectionality in machine learning. Ramaswamy also investigates human interpretability of visual explanations and evaluates the effectiveness of concept-based explanations. His research includes developing datasets for object recognition and analyzing gender artifacts in visual data. He emphasizes the importance of dataset choice, concept learnability, and human capability in creating fair and interpretable AI systems.