This forum is inactive. Browsing/searching possible.
Connect your moderator Slack workspace to receive post notifications:
randomized smoothing
Lectures
·
69
·
1
·
12 Jan '21
Hello,
I don't understand this explanation. So we have a point x that has expected value of clas…
Data augmentation
Lectures
·
73
·
2
·
11 Jan '21
In lecture 9b (Data augmentation for neural networks), is the rotation of the numbers here (Data au…
Why does adding w*sgn(w) subject perturbed data to upper bound of max norm (epsilon)?
Lectures
·
54
·
1
·
7 Jan '21
In the paper describing the fast gradient sign method, the authors explain why adversarial samples …
Adversarial training and Randomized smoothing
Lectures
·
97
·
1
·
3 Jan '21
Hello! I have two questions related to the lecture about Adversarial ML.
1. In the paragraph abou…
Adversarial risk in high dimension
Lectures
·
122
·
2
·
29 Dec '20
Hello,
I have a question regarding adversarial risk in high dimension. Based on the first exampl…
Randomised Smoothing: Upper bound on allowed perturbation
Lectures
·
118
·
3
·
24 Nov '20
I was wondering what is the relationship between the maximum scale of the adversarial perturbation …
Lecture notes (9c - page 19) - Why is there twice a min?
Lectures
·
66
·
2
·
23 Nov '20
Hi,
I don't understand why we have two mins over theta in the lecture notes...
 mentioned that"The first compon…
Analysis of the bayes classifier: scaling everything by a constant
Lectures
·
75
·
3
·
10 Nov '20
Hi,
I have a question concerning the end of the analysis of the bayes classifier using all featu…