# Team daheimao solution

Code and documentation can be found
[here](https://github.com/stupiding/kaggle_EEG)
.
I am a Ph.D student majored in neural networks and computer vision. This is my first Kaggle competition. My intention of participating in this competition is to evaluate the performance of recurrent convolutional neural network (RCNN) in processing time series data. RCNN is firstly proposed by I for image classification (
[CVPR 2015](http://www.xlhu.cn/papers/Liang15-cvpr.pdf)
), and then used for scene labeling (will appear in
[NIPS 2015](https://nips.cc/Conferences/2015/AcceptedPapers)
soon). In these two tasks input data is static image, and RCNN performs well. It turns out that RCNN also performs well for EEG data. Without any domain knowledge related modification, our best single model achieves 0.97652/0.97661 public/private LB scores.
The pipeline of our solution is simple:
1.A set of candidate models (mostly RCNN) are trained in a 4-fold cross validation (CV) manner over the training set.
2.Greedy forward selection (GFS) is applied to the candidate model set, so that some models are selected for combination and submission.
The selected models are re-train over all the training data, and their predictions over the test data are averaged and submitted.
The pre-processing is very simple, just removing the mean of each input sample, which is the common practice in image classification. The model is neither subject-specific nor event-specific. A model receives the data of any subject as input, and outputs six predictions.
Most of our models are RCNN, whose structure is described in the
[documentation](https://github.com/stupiding/kaggle_EEG/blob/master/README.md)
and the papers. I also tried CNN, and the best CNN model achieves 0.97136/0.97297 public/priviate LB scores.
GFS seems to work well and its results are consistent with the LB scores. However, I made some mistakes when there were 3 days before the deadline. And our ensemble almost stops improving since then.
To sum up,  my first kaggle competition is very exciting. I want to give thanks to the organizers and all the other teams!