This is the repository for the second challenge hosted by Politecnico di Milano for the Artificial neural networks and deep learning course in 2022. In this task, we are required to correctly classify samples in the multivariate time series format. In other words, 6 different time series are provided and the goal is to classify them with a single label among 12 possible labels.
The source of these time series is unkown, thus we can not apply any domain knowledge.
Here you can see the measurements:
You can find the dataset here
Total accuracy on the test set: 0.745
Wish | Another | Comfortably | Money | Breathe | Time | Brain | Echoes | Wearing | Sorrow | Hey | Shine | |
---|---|---|---|---|---|---|---|---|---|---|---|---|
F1 score | 0.7450 | 0.4737 | 0.6358 | 0.9580 | 0.5859 | 0.2963 | 0.5 | 0.8704 | 0.4286 | 0.9630 | 0.7789 | 0.99 |
position 20th out of 201
Our professor give us ? out of 5 points for the exam.