time-series-forecasting-with-UORO-RTRL-LMS-and-linear-regression

Prediction of multidimensional time-series data using a recurrent neural network (RNN) trained by real-time recurrent learning (RTRL), unbiased online recurrent optimization (UORO), least mean squares (LMS), or multivariate linear regression. The optimal hyper-parameters are selected using grid search with parallel processing.

Lucas-Kanade-pyramidal-optical-flow-for-3D-image-sequences

Implementation of the Lucas-Kanade pyramidal optical flow algorithm to register 3D medical images; 1st repo in a series of 3 repos associated with the research article "Prediction of the motion of chest internal points using an RNN trained with RTRL for latency compensation in lung cancer radiotherapy" (Pohl et al, Comput Med Imaging Graph, 2021)

Time-series-prediction-with-an-RNN-trained-with-RTRL

Multidimensional time-series data prediction with a recurrent neural network (RNN) trained by RTRL; 2nd repo in a series of 3 repos associated with the research article "Prediction of the motion of chest internal points using an RNN trained with RTRL for latency compensation in lung cancer radiotherapy" (Pohl et al, Comput Med Imaging Graph, 2021)

3D-image-warping-using-Nadaraya-Watson-non-linear-regression

Deforming a 3D image according to a given deformation vector field with Nadaraya-Watson regression; 3rd repo in a series of 3 repos associated with the research article "Prediction of the motion of chest internal points using an RNN trained with RTRL for latency compensation in lung cancer radiotherapy" (Pohl et al, Comput Med Imaging Graph, 2021)