Brain-Machine Interfacing Projects
VR Demonstration of Neuroprosthesis Vision
Last Update: 02.10.2024
Status: OPEN
Type: bachelors/masters (short/long)
Contact: Niklas Hahn (niklas@ini.uzh.ch), Prof. Shih-Chii Liu (shih@ini.uzh.ch)
___________________________________________
We are interested in building a VR based tool for demonstrating the visual neuroprosthesis output as part of the NeuraViPeR project. As part of demonstration the VR Headset will simulate a limited phosphene based output for a patient for the non-visually impaired participant. These outputs will be generated by a deep neural network or a spiking neural network that will be used for patients.
The participant will be asked to take part in a basic task using the simulated output, an example of a task vs simulated view can be seen below. We are interested in developing such a system that functions on a standard VR headset (Meta or homemade) and running some basic user studies.
Possible topics are/include:
Implementing a phosphene simulator (e.g.https://github.com/neuralcodinglab/dynaphos ) on a standalone VR headset (like META 2)
Investigating the stacking & switching of multiple task-optimized DNN for Phosphene-Vision
Creating an event camera Dataset (DVS) to train AI-Agents of real-life data
Using hls4ml create a demo to run an image-2-brainstimulation NN on an FPGA
Cortical feedback-loop in visual neuroprosthetics
Last Update: 02.10.2024
Status: OPEN
Type: bachelors/masters (short/long)
Contact: Niklas Hahn (niklas@ini.uzh.ch), Prof. Shih-Chii Liu (shih@ini.uzh.ch)
___________________________________________
As part of the NeuraViPeR project, we aim to explore potential applications of neural recordings in a closed-loop system for visual prostheses. The primary goal is to optimize electrically stimulated visual perceptions, or phosphenes. To achieve this, we employ novel flexible electrodes and have conducted neural recordings during brain stimulation experiments in rats.
Possible topics are/include:
Analyze the cerebral recording of a rat to optimize visual stimulation for a closed loop setup
Using a Neural Network to optimize stimulation patterns accordingly to the brain recordings
Implementing the analysis algorithm / feedback loop on a portable platform (jetson or FPGA)