Email Address: email@example.com
I completed my MSc in System on Chip (in 2011) and PhD in Electrical & Electronics Engineering (in 2016) from the School of Electronics & Computer Science, University of Southampton. My doctoral research focused on the application of Gaussian processes for accelerating the ABC-SMC algorithm for learning dynamical systems. I applied this method to fit plant electrophysiological models to experimental data. Following my PhD, I was a postdoc at the Computer Science Department, University of Oxford (2015-2018), where I was developing machine learning and Bayesian statistical methods to carry out inference, uncertainty quantification and experimental design for cardiac models. Currently, I am working on developing efficient approximate Bayesian inference techniques for Bayesian evidence synthesis. Such efficient inference techniques are necessary for real-time monitoring of epidemics.
I am interested in developing efficient and automated methods for carrying out calibration, sensitivity analysis and uncertainty quantification tasks in a variety of complex biological systems. For developing such methods I primarily work on Bayesian inference and modern machine learning techniques such as sequential Monte Carlo (SMC), approximate Bayesian computation (ABC), Gaussian processes, Bayesian deep learning, black-box variational inference and differentiable probabilistic programming. I am also interested (since my MSc days) in computational matters and thus some of my research effort is spent on a range of computational issues ranging from designing libraries for MCMC to fixed-point hardware (FPGA/ASIC) implementations of machine learning algorithms.
- Sanmitra Ghosh, David Gavaghan, Gary Mirams, “Gaussian process emulation for discontinuous response surfaces with applications for cardiac electrophysiology models”, (Under review). (preprint: arXiv:1805.10020v1)
- Sanmitra Ghosh, Srinandan Dasmahapatra, Koushik Maharatna, “Fast approximate Bayesian computation for estimating parameters in differential equations”, Statistics and Computing, 2017.
- Sanmitra Ghosh,“Fast approximate Bayesian computation for inference in non-linear differential equations”, Doctoral Thesis, 2016.
- Saptarshi Das, Barry Juans Ajiwibawa, Shre Chatterjee, Sanmitra Ghosh, Koushik Maharatna, Srinandan Dasmahapatra, Andrea Vitaletti, Elisa Masi, Stefano Mancuso, “Drift removal in plantelectrical signals via IIR filtering using wavelet energy”, Computers and Electronics in Agriculture, 2015.
- Shre Chatterjee, Sanmitra Ghosh, Saptarshi Das, Veronica Manzella, Andrea Vitaletti, Elisa Masi, Luisa Santopolo, Stefano Mancuso and Koushik Maharatna, “Forward and inverse modelling approaches for prediction of light stimulus from electrophysiological response in plants”, Measurement, 2014.