Logo

Harvard Learning Seminar - Shared screen with speaker view
Kenneth Chiu
38:26
Just curious, what happens when you feed this network actual pure noise?
Colin Rowat
50:40
does the low bias deflect mean zero noise?
Colin Rowat
50:53
*reflect
Abhinav Kumar
54:40
Batch Norm should cancel the effect of bias in the network even if bias is present. Why is Batch Norm not able to cancel the bias in DnCNN ?
Abhinav Kumar
58:34
Thankyou
John M.
01:03:13
How many of the removed constants were non-zero?
John M.
01:04:08
thanks
John M.
01:18:31
A couple of questions if possible:
John M.
01:23:36
sorry in the end
Talia Konkle
01:36:03
Can you give an intuition for why is the p(y) is getting finer and finer over iterations (blurry to fine)?
Suresh
01:50:54
sorry, it was accidental touch while gripping my mobile...
John M.
02:00:23
What is the chance the interpretation of the cone of the denoiser in 3D would change if you change your objective?
Agi Kajanaku
02:00:28
Thank you!
Dushyant Mehra
02:00:42
Great Talk, have you looked into other metrics besides SSIM to assess image quality?
John M.
02:01:18
yeah
John M.
02:09:11
Once we have obtained the prior and from the examples shown seems pretty good would that be affected if the input changes? Think of prior obtained from grey scale inputs and trying to apply to rgb inputs?