RoshanRane

ML_for_IMAGEN

PredNet-and-Predictive-Coding-A-Critical-Review

Performing video classificaiton by using the predictive processing architecture. The model is trained in a self-supervised manner to predict the next frames in videos along with the supervised video action classification task.

segmentation-moving-MNIST

The Moving-MNIST video dataset reformulated for the task of semantic segmentation.

active_vision_prednet

3 research questions shall be tackled in this project -

toybrains

Create a synthetic dataset with toy images of brain MRI slice (2D). Can be used to control for

bih-cluster

BIH Cluster Wiki

Deep-learning-with-Pytorch-and-FashionMNIST

Demonstration of training and developing CNNs using Pytorch for Fashion-MNIST dataset

Deviance_explained

Deviance explained metric implemented in python

roshanrane.github.io

RST-parser

End-to-end automatic RST parser using neural networks. This team-project is developed as part of the Masters course ANLP at the University of Potsdam.

tinyYOLO-on-RaspberryPi

A tinyYOLO model implementation with tensorflow to be deployed on a RaspberryPi. The model is trained to detect vehicles in a real-time video captured by the camera mounted on the Raspberry Pi