This repository resembles our solution approach to the second PSDA task.
It consists of three relevant Jupyter-Notebooks:
## 1. `data_exploration.ipynb`
@Anastasia schreib mal hier was pls
## 2. `Neural.ipynb`
Experiments and results on implementing and tuning a single neural network model.
The model's task is to predict the future operability of wind turbines in a single exemplary region.
The notebook contains RNNs and one-dimensional CNNs that aim to achieve this task.
The best validation result can be observed for CNNs with depth-wise separable convolutions, as RNNs and regular CNNs show a tendency to overfit on the given data, despite heavy regularization.
## 3. `NeuralEnsemble.ipynb`
To tackle the concept drift problematic occuring in the testset, we combine several neural models into one ensemble.
Each of the models is trained on a single region of wind turbines.
The models' predictions are combined by using a weighted majority vote.
More specifically, the models' output probabilities are acquired via softmax and averaged to form the ensemble's output.