Talk:Deep learning

I am considering adding information regarding power consumption. Currently I see two directions: low-power inference for embedded devices{{Cite journal|last=Gauen|first=Kent|last2=Rangan|first2=Rohit|last3=Mohan|first3=Anup|last4=Lu|first4=Yung-Hsiang|last5=Liu|first5=Wei|last6=Berg|first6=Alexander C.|date=2017-01|title=Low-power image recognition challenge|url=http://ieeexplore.ieee.org/document/7858303/|journal=2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC)|location=Chiba|publisher=IEEE|pages=99–104|doi=10.1109/ASPDAC.2017.7858303|isbn=978-1-5090-1558-0}} and low-power training for huge networks{{Cite journal|date=2019-12-01|title=Estimation of energy consumption in machine learning|url=https://www.sciencedirect.com/science/article/pii/S0743731518308773|journal=Journal of Parallel and Distributed Computing|language=en|volume=134|pages=75–88|doi=10.1016/j.jpdc.2019.07.007|issn=0743-7315}}. Please let me know if you know of more credible and/or overview sources discussing the concerns. p.s. This may be a discussion for another page, e.g. ML or ANNs. Cheater no1 (talk) 13:16, 13 November 2020 (UTC)

==Planned slow motion cleanup of reference spamming and overciting==

I plan to attempt a slow motion cleanup of reference spamming. The typical case is an obscure non-notable paper where it does a poor job of supporting the items which cited it, particularly where the material is still cited without it. When all of the references looked equally good/applicable on overcited items, I left them all in. Sincerely, North8000 (talk) 16:29, 7 March 2022 (UTC)

• Completed through the first image and lead. North8000 (talk) 20:20, 7 March 2022 (UTC)
• Completed through the first 5 paragraphs of the overview section. North8000 (talk) 22:43, 7 March 2022 (UTC)
• Completed through end of overview section. North8000 (talk) 02:54, 8 March 2022 (UTC)
• Complete through interpretation section. That section still has some over-cited items, but the remaining ones all look useful. North8000 (talk) 17:56, 14 March 2022 (UTC)
• Complete through 1st 13 paragraphs of history section.North8000 (talk) 18:16, 14 March 2022 (UTC)
• Complete through history section including revolution subsection.North8000 (talk) 21:04, 15 March 2022 (UTC)
• Complete through the Neural Networks section including all subsections. North8000 (talk) 14:23, 17 March 2022 (UTC)
• Complete through hardware section. North8000 (talk) 00:07, 18 March 2022 (UTC)
• Completed the articleNorth8000 (talk) 02:54, 18 March 2022 (UTC)

{{reflist-talk}}

{{dashboard.wikiedu.org assignment | course = Wikipedia:Wiki_Ed/New_York_University/Research_Process_and_Methodology_-_FA23_-_Sect_202_-_Thu_(Fall,_2023) | assignments = HELLOEXTRACREDIT | start_date = 2023-09-06 | end_date = 2023-12-14 }}

— Assignment last updated by HELLOEXTRACREDIT (talk) 04:30, 26 November 2023 (UTC)

This is a reply to the question posed by you [https://en.wikipedia.org/w/index.php?title=Deep_learning&oldid=prev&diff=1249530723 here]. I reverted the edit by the IP because the range {{ip|194.247.67.196/30}} quite clearly inaproppriately promoted the article by Murray et. al., e.g. [https://en.wikipedia.org/w/index.php?title=Asylum_seeker&diff=prev&oldid=1248231105], [https://en.wikipedia.org/w/index.php?title=Age_of_majority&diff=prev&oldid=1248793359]. This leads me to think it is a spam campaign, so I reverted all edits citing this article (all of them were from this range). Janhrach (talk) 12:11, 5 October 2024 (UTC)

:@Janhrach Thanks for responding. It's a primary source showing the existence of an application, but it's not necessarily a notable application without secondary sourcing.WeyerStudentOfAgrippa (talk) 12:24, 5 October 2024 (UTC)

{{dashboard.wikiedu.org assignment | course = Wikipedia:Wiki_Ed/University_of_Arizona/Linguistics_in_the_Digital_Age_(Fall_2024) | assignments = Eiaohdsnkafpas | start_date = 2024-08-26 | end_date = 2024-12-11 }}

— Assignment last updated by Kofiasa (talk) 22:41, 1 November 2024 (UTC)

:@ 45.139.161.114 (talk) 14:02, 24 November 2024 (UTC)