State Representation Learning (SRL) zoo with PyTorch - Part of S-RL Toolbox

Differentiable Cosmological Forward Model

A tutorial on forward models for model-based reinforcement learning.

Approximate forward models of fluxes and spectra time-series of non-uniform stars

CarboCATLite model by Peter Burgess

Analysis of robust classification algorithms for overcoming class-dependant labelling noise: Forward, Importance Reweighting and T-revision. We demonstrate methods for estimating the transition matrix in order to obtain better classifier performance when working with noisy data.

Diffuse Optical Tomography (DOT) is an non-invasive optical imaging technique that measures the optical properties of physiological tissue using near infrared spectrum light. Optical properties are extracted from the measurement using reconstruction algorithm. This project uses the steepest descent method for reconstruction of optical data.