deep learning

This is the unpaired image-2-image and volume-2-volume translation project. It converts images or volumes of an input domain to a target domain using artificial intelligence.

This is a project to train, use and analyze 2D and 3D neural networks for segmentation.

This is a project to train, use and analyze 2D and 3D neural networks for segmentation. It contains a UI and is implemented in pytorch and django as backend.

The frontend for SmartIntentNN

The deep learning model and backend of SmartIntentNN

Implementation of Movement Aid for the Visually-Impaired by Using CNN based Learning Architecture

A virtual space with your virtual twin. Your twin can interact with other twins and other people.

Exploring and Visualizing Referring Expression Comprehension (Bachelor's Thesis by David Álvarez Rosa)

Implementation and Analysis of a NN-based pressure predictor for Eulerian Fluid Simulation. Training includes the solver itself and aims to produce a result that can be fed back into the solver to achieve high accuracy in relatively few iterations.

The AI that replaces Ernst Billgren

Domain specific language for generating analogous variations of textual inputs