Rudrasis Chakraborty
Research Scientist | Machine Learning & Statistical Modeling Expert
Explore My ResearchAbout Me
I am a research scientist specializing in statistical modeling, machine learning, and manifold-valued data analysis. My work focuses on developing innovative recurrent neural network architectures for complex data structures, with applications in computer vision, medical imaging, and signal processing.
Featured Research
ManifoldNet: A Deep Neural Network for Manifold-Valued Data With Applications
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2022
Theoretical framework for deep neural networks handling manifold-valued data using weighted Fréchet means, with applications to computer vision and medical imaging. Featured in top-tier AI journal with significant impact.
Intrinsic Grassmann Averages for Online Linear, Robust and Nonlinear Subspace Learning
IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) 2021
Geometric framework for computing principal linear subspaces using intrinsic averaging on Grassmann manifolds, with applications to robust PCA and kernel PCA. Extended version of highly cited CVPR 2017 paper.
Statistical Recurrent Models on Manifold Valued Data
Neural Information Processing Systems (NeurIPS) 2018
Novel approach to handling sequential data on Riemannian manifolds using statistical recurrent units, with applications to medical imaging and computer vision tasks. Published at top ML venue.
Research Expertise
Machine Learning
- Recurrent Neural Networks
- Statistical Modeling
- Deep Learning
- Computer Vision
Mathematical Foundations
- Manifold Learning
- Riemannian Geometry
- Statistical Analysis
- Optimization
Applications
- Medical Imaging
- Signal Processing
- Data Analysis
- Scientific Computing