This repository is about learning unknown parameters from data under uncertainty using Bayesian inference.
It focuses on how prior assumptions, likelihood models, and observed data combine to form posterior distributions, and how inference behaves in practical and challenging settings.
Topics (in progress):
- Bayesian parameter estimation
- Posterior distributions and uncertainty
- MAP and posterior mean estimation
- Sampling-based inference (MCMC)
- Identifiability and prior sensitivity
- Practical diagnostics and failure cases
🚧 This repository is under active development. Code, experiments, and explanations will be added step by step.
I am interested in probabilistic methods for robots, with an emphasis on state estimation, control, and uncertainty quantification.
Feel free to reach out:
- Email: sampath@umich.edu
- LinkedIn: https://www.linkedin.com/in/sai-sampath-kedari