Results 16 comments of Thomas Tanay

Thanks for letting me know, I hadn't noticed on my computer. This raises a more general issue: I will have to check that the page displays correctly across operating systems/web...

Quick update: - I've changed the style of the abstract, hopefully stimulating the reader's curiosity: ![abstract](https://user-images.githubusercontent.com/23214134/35990572-54bbbd1c-0cfc-11e8-9a6e-b492a7f808a0.png) - I've made a few modifications to the “SVM on MNIST” section, based on...

After reflection, I agree that making the toy problem independent of the dimension might be confusing to the reader. It might be clearer to focus on the 2-dimensional case first,...

I like this idea and will try to add more diagrams (I like the "construction of adversarial examples" one for instance). Do you recommend a specific tool for the creation...

I agree, it looks better with a contour. Actually it might be a good idea to do the same on the outer square, as it is sometimes difficult to distinguish...

Thank you for all the comments! > “I’d be surprised if this is the first work to give a relationship between weight decay and distance from the data to the...

These are all very good points. My initial objective was indeed to make a short visual abstract, but I got caught into trying to summarize everything. I will probably go...

I just submitted a new version with a simplified abstract: ![abstract](https://user-images.githubusercontent.com/23214134/31493216-1a2cb21e-af46-11e7-9c51-92f4844d1c06.png) I am not completely satisfied with the design though, I will try to improve it in the coming days.

Here is what I have now: ![abstract](https://user-images.githubusercontent.com/23214134/31508474-18dae054-af76-11e7-9b3c-e3a46dd3080c.png)

ah that's a good point. At the moment the orange is the margin but I don't refer to it that much in the text. I could replace that by the...