Skip to main content
Data Science

Timeline for What are deconvolutional layers?

Current License: CC BY-SA 4.0

10 events
when toggle format whatbylicensecomment
May 10, 2021 at 16:41commentadded eric links are not answers
Apr 26, 2020 at 9:18commentadded amin msh towardsdatascience.com/…
Oct 25, 2019 at 17:19commentadded Yossarian42 The link seems to be fairly old staff. It would be better that you could summary the material in several words.@Stephen Rauch
Jun 21, 2018 at 13:21history edited Stephen Rauch♦CC BY-SA 4.0
More explanation
Jun 21, 2018 at 6:14review Low quality posts
Jun 21, 2018 at 13:21
Dec 19, 2015 at 13:34commentadded SmallChess Although the links are good, a brief summary of the model in your own words would have been better.
Jun 20, 2015 at 11:08commentadded Neil Slater A full summary is not required, just a headline - e.g. "A deconvolutional neural network is similar to a CNN, but is trained so that features in any hidden layer can be used to reconstruct the previous layer (and by repetition across layers, eventually the input could be reconstructed from the output). This allows it to be trained unsupervised in order to learn generic high-level features in a problem domain - usually image processing" (note I am not even sure if that is correct, hence not writing my own answer).
Jun 20, 2015 at 9:11commentadded Azrael I am sorry but the content of these pages is too large to be summarized in a short paragraph.
Jun 20, 2015 at 7:01commentadded Neil Slater Is it possible to summarise the content of any one of those links, in a short paragraph? The links might be useful for further research, but ideally a stack exchange answer should have enough text to address the basic question without needing to go off site.
Jun 19, 2015 at 10:17history answered AzraelCC BY-SA 3.0
close