Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
DeepEye: Predicting Gaze Position with Deep Learning of Electroencephalography Data
The aim of this project is to investigate Machine Learning models to predict eye gaze from Electroencephalography (EEG) data on a newly available large-scale dataset.
Keywords: Deep Learning, Machine Learning, Eye Gaze, EEG
Deep Learning is inspired by the brain structure. But can deep learning help us to advance our understanding of brain functions?
This project aims to develop an eye-tracking approach that offers gaze position that is based on concurrently measured electroencephalography (EEG) data. EEG is a widely-used, safe and cost-friendly method in cognitive neuroscience that directly measures the brain's electrical activity and enables measurement in clinical settings.
In this project, you will have the opportunity to work on a new large dataset of the simultaneously recorded electroencephalography and eye-tracking data of 450 participants. Hitherto, we have presented the benchmark for eye movement prediction (https://openreview.net/forum?id=Nc2uduhU9qa accepted to NeurIPS 2021). The next project milestone aims to improve the algorithms and understanding of the good performance of the current baselines.
Requirements: Knowledge in Deep Learning, solid background in Machine Learning. Implementation experience with TensorFlow or Pytorch is an advantage.
Deep Learning is inspired by the brain structure. But can deep learning help us to advance our understanding of brain functions?
This project aims to develop an eye-tracking approach that offers gaze position that is based on concurrently measured electroencephalography (EEG) data. EEG is a widely-used, safe and cost-friendly method in cognitive neuroscience that directly measures the brain's electrical activity and enables measurement in clinical settings.
In this project, you will have the opportunity to work on a new large dataset of the simultaneously recorded electroencephalography and eye-tracking data of 450 participants. Hitherto, we have presented the benchmark for eye movement prediction (https://openreview.net/forum?id=Nc2uduhU9qa accepted to NeurIPS 2021). The next project milestone aims to improve the algorithms and understanding of the good performance of the current baselines.
Requirements: Knowledge in Deep Learning, solid background in Machine Learning. Implementation experience with TensorFlow or Pytorch is an advantage.
Not specified
Martyna Plomecka (martyna.plomecka@uzh.ch)
Manuel Kaufmann (manuel.kaufmann@inf.ethz.ch)
Martyna Plomecka (martyna.plomecka@uzh.ch) Manuel Kaufmann (manuel.kaufmann@inf.ethz.ch)