GAN for augmentation of tabular data in python
Budget: €60 – €120 EUR
By using generative adversarial networks (GAN) the aim is to produce artificial signals of electroencephalograms (EEG). All signals are the form of X vs Y (tabular data) and are like the image below.
The successful bidder must comment the python code and explain (in a short paragraph or graph) the algorithmic approach used. The evaluation of the results must be given with the following metrics: Root Mean Square Error (RMSE), Percent Root Mean Square Difference (PRD), Mean Absolute Error (MAE), and Fréchet Distance (FD). Pytorch or Tensorflow implementations are welcome.
The successful bidder must comment the python code and explain (in a short paragraph or graph) the algorithmic approach used. The evaluation of the results must be given with the following metrics: Root Mean Square Error (RMSE), Percent Root Mean Square Difference (PRD), Mean Absolute Error (MAE), and Fréchet Distance (FD). Pytorch or Tensorflow implementations are welcome.