9bdb8b1faffa4b3d41779bb495d79fb9-AuthorFeedback.pdf

Thank you very much for the thorough and generally positive feedback. R1.1 However, I worry about the reproducibility since most of the results are run by only once. A1.1 Upon acceptance we will publish the source code, implemented in Tensorflow, that was also submitted with this R2.1 For the equation between line 135 and 136(why does it not have a equation number?): A2.1 We will add an equation number. The experiments stops on L=20.