We thank the Reviewers for their comments and their positive feedback both on the problem we decided to tackle and

We did our best to answer the provided questions and to reply to some comments. " Are the resulting features better able to perform some task of interest? " We considered the problem of MI-based features were helping in case of small/sparse supervision. " The paper introduces fourth order dynamics, and spends considerable time simplifying this to 2nd order dynamics. " The experiments chose hyperparameters to maximize the mutual information extracted by each algorithm, and it is not We selected the parameters that were leading to the largest MI index at the end of the learning stage, Eq. (8), and not on " The evaluation videos could be better motivated. How many loops were necessary [...]" We selected " The authors need to contrast their work with that of Friston and point out the novel contributions In the experiment [...] fixation/attention locations generated by other state-of-the-art video Bruce and Tsotsos attention emerges maximizing the Self-Information of each local image patch. " (Thm 1) and its proof in the supplementary seem correct, but no learning algorithms are given [...] " " Couldn't understand how exactly the trajectory density estimation, on which the mutual information estimation is based, " We compared different choices for the function " What is actiually assumed about the unknown potential U?How is it learned from the data?