Susi

- [ADDED] Semi-supervised abilities for classifier and regressor
- [ADDED] Example notebooks for semi-supervised applications
- [ADDED] Tests for example notebooks
- [FIXED] Code looks better in documentation with sphinx.ext.napoleon
- [CHANGED] Requirements for the SUSI package
- [REMOVED] Support for Python 3.4

- [ADDED] PCA initialization of the SOM weights with 2 principal components
- [ADDED] Variable variance
- [CHANGED] Moved installation guidelines and examples to documentation

**Changes:**
- [ADDED] Batch algorithm for unsupervised and supervised SOM
- [ADDED] Calculation of the unified distance matrix (u-matrix)
- [FIXED] Added estimator_check of scikit-learn and fixed recognized issues

- [ADDED] Link to arXiv paper
- [ADDED] Mexican-hat neighborhood distance weight
- [ADDED] Possibility for different initialization modes
- [CHANGED] Simplified initialization of estimators
- [FIXED] URLs and styles in documentation
- [FIXED] Colormap in Salinas example