The paper proposes a form of recurrent network built out of quantum neurons. The model is novel and interesting and the paper has a good amount of discussion and experiments and should make good and interesting paper at neurips. One important improvement that should be made for writing the paper is to make it more accessible to people at neurips. The reviewers for this paper ranged from those with very little background in the field to an expert and therefore the reviews provide a lot of comments on what is not clear in the paper and what should be improved. The paper should be understandable to someone that knows neural networks and basic quantum mechanics but nothing about quantum computation. It should also be somewhat understandable for a person without background in quantum mechanics: The core properties should be *abstracted* in such way that it is clear what the exact classical computation (as you run it classical computer) is being executed by this network - what is the hidden space, what is the set of parameters, the update and scaling with the number of quantum neurons and how would this computation run more efficiently if we had an actual quantum operations. This is be in the main text, not supplement.