| # Use case with Support Vector Machine |
| |
| To ensure that not only the implementation is learning, but is able to outsmart the softmax, as [this article](arxiv.org/pdf/1306.0239.pdf) suggests, I ran svm_mnist.py script. It was based on the MNIST experiment description on the article and [this tutorial](https://github.com/dmlc/mxnet-gtc-tutorial/blob/master/tutorial.ipynb). |
| |
| |
| ## To this you will need |
| |
| * [Numpy](http://www.scipy.org/scipylib/download.html) |
| * [Sklearn](http://scikit-learn.org/stable/install.html) |
| |
| I recommend installing [matplot](http://matplotlib.org/users/installing.html) to visualize examples |
