Inside this repo you will find the baseline solution for the Ariel Data Challenge. To run the script you will need access to the training and test data, both of which can be found here. There are two ways to run the baseline:
python baseline_MCDropout.py --training PATH/TO/TRAININGDATA/ --test PATH/TO/TESTDATA
We trained a neural network to perform a supervised multi-target regression task. The architecture of the network is modified from the CNN network as described in Yip et al.
At test time we performed Monte Carlo Dropout to provide a mutlivariate distribution for each test example. Samples from the mutlivariate distribution is submitted to the regular track. Quartiles estimates are extracted from the same distribution to submit to the light track.
There are different direction to take from here on, let us summarise the shortcoming of this model:
The data preprocessing is quite simplitic, we list the limitations below:
QuartilesTable.csvfor Light Track and
Tracedata.hdf5for Regular Track), which are the GT for this competition.