Deep auditory encoding with self-attention to predict brain activity
This Python package allows you to train a recurrent DNN (a GRU) and learn a self-attention mechanism that weighs hidden states.
This Python package allows you to train a recurrent DNN (a GRU) and learn a self-attention mechanism that weighs hidden states.
This was my first Kaggle challenge that I took seriously and I managed to get into the top 3% (119th place out of 4550 teams) - nothing to brag about, but a great learning experience nonetheless. You can find my solution here.
Do you have a BIDS-compliant dataset and stimulus and want to train and validate voxel-wise encoding models in a reproducible workflow? Using this BIDS app, this is as easy as writing a single line in your terminal.