Wikipedia:Articles for deletion/Multimodel Deep Learning

The following discussion is an archived debate of the proposed deletion of the article below. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.

The result was delete. Sandstein 18:22, 17 June 2018 (UTC)[reply]

Multimodel Deep Learning

[Hide this box] New to Articles for deletion (AfD)? Read these primers!

(Find sources: Google (books · news · scholar · free images · WP refs) · FENS · JSTOR · TWL)

"Random Multimodel Deep Learning" is an article based solely on the work of Kowsari, Kamran (first reference). All other references are not on "multimodel deep learning". The Kowsari work has 0 citations, and was just published. This clearly fails the WP:GNG, and thus I opt for delete. Do not let yourself be mislead by all the unrelated references in the wikipedia article. There is a link to Theano, but Theano does not include RMDL. Similarly, the "history" section explains what "ensemble learning" and "deep learning" are, not RMDL - wiki references 2-6 are not based on, or using RMDL, but older prior work that does not support this article. HelpUsStopSpam (talk) 11:30, 10 June 2018 (UTC)[reply]

Delete Some of the concerns raised by the nom are valid. Some aren't. The Kowsari work has 56 references, inline citations are not necessarily required, but are present anyway. The other issues of not mentioning RMDL are somewhat a non-issue. The article doesn't claim them as supporting RMDL, they're in the history section. Other !voters don't need to dive into those references, it's fairly clear that this article only cites one source. The nom is right about failure of GNG, and the whole article reeks of OR. Kill it with ~~fire~~ adminium. ∰Bellezzasolo✡ Discuss 12:40, 10 June 2018 (UTC)[reply]

Note: This discussion has been included in the list of Computing-related deletion discussions. MT Train^Talk 17:27, 10 June 2018 (UTC)[reply]

I didn't say anything about the references (56 or not) in his publication? I noted that RMDL is not cited independently. The reason why I emphasized this is because people tend to defend articles by "but it is full of references"; but if they only reference prerequisites, not the notability of the article subject, one has to carefully check which wikirefs matter for judging GNG. This in particular applies for the link to Theano - this easily gives the false impression, RMDL would be in Theano. But it isn't. HelpUsStopSpam (talk) 19:50, 11 June 2018 (UTC)[reply]

I pruned all the generic "deep learning" references and further reading to make it a bit clearer, and to make the article more focused (no need to re-tell the story of deep learning). So if anyone get into this discussion at a later point, and is wondering what "other" references I talked about. HelpUsStopSpam (talk) 19:57, 11 June 2018 (UTC)[reply]

Delete This article is primarily based on a new arxiv paper that is not yet published. I was unable to find any reliable sources about RMDL, much less independent RS. Without independent reliable sources, there can be no verification and should be no article. --Mark viking (talk) 23:51, 11 June 2018 (UTC)[reply]
Comment - probably WP:TOOSOON. Haven't found confirmation of Best Paper Award for the (small?) conference or even if they presented there, but maybe it wasn't by the primary author. Had reported best results for MNIST with their ensemble. Maybe if it was at one of big conferences it would have had more press. StrayBolt (talk) 22:45, 16 June 2018 (UTC)[reply]

The above discussion is preserved as an archive of the debate. Please do not modify it. Subsequent comments should be made on the appropriate discussion page (such as the article's talk page or in a deletion review). No further edits should be made to this page.