Deep learning: Revision history

Filter revisionsshowhide

To date:

Tag filter:

Invert selection

External tools:

For any version listed below, click on its date to view it. For more help, see Help:Page history and Help:Edit summary. (cur) = difference from current version, (prev) = difference from preceding version, m = minor edit, → = section edit, ← = automatic edit summary

curprev 03:5803:58, 21 November 2024 Citation bot talk contribs 185,170 bytes −56 Added issue. Removed URL that duplicated identifier. | Use this bot. Report bugs. | #UCB_CommandLine undo

curprev 03:0303:03, 16 November 2024 Mikhail Ryazanov talk contribs m 185,226 bytes 0 MOS:LQ undo

curprev 21:4021:40, 14 November 2024 Viktor Guer talk contribs 185,226 bytes +4 →Further reading undo

curprev 13:1913:19, 11 November 2024 MariRinjah talk contribs m 185,222 bytes −2 →Partial differential equations: Changed a minor error: "[...] methods rely on" instead of "[...] methods relies on" undo

curprev 19:0719:07, 10 November 2024 R'n'B talk contribs m 185,224 bytes +25 Disambiguating links to Strong AI (help needed) using DisamAssist. undo

curprev 02:2402:24, 5 November 2024 Aadirulez8 talk contribs m 185,199 bytes −4 v2.05 - Fix errors for CW project (Reference before punctuation - Reference tags without correct match - Unbalanced quotes in ref name or illegal character.) / Help needed to fix 1 links to disambiguation pages - Strong artificial intelligence undo Tag: WPCleaner

curprev 20:4120:41, 3 November 2024 Lfstevens talk contribs 185,203 bytes −431 Filled in 0 bare reference(s) with reFill 2 undo
curprev 08:0608:06, 3 November 2024 2406:3003:2002:be4:f9d7:e327:20bb:455a talk 185,634 bytes +1,650 →Added two missing references and included the just enough complexity research into the list of attempts to reduce overfitting undo

curprev 05:5905:59, 2 November 2024 Citation bot talk contribs 183,984 bytes −28 Removed parameters. | Use this bot. Report bugs. | #UCB_CommandLine undo

curprev 17:0817:08, 23 October 2024 Perceptron599 talk contribs 184,012 bytes +113 Fix misleading sentence; neural networks are used for more than just representation learning undo Tags: Mobile edit Mobile web edit
curprev 16:3716:37, 23 October 2024 Perceptron599 talk contribs 183,899 bytes −398 Revert edit by Khethan (wrong place for paragraph / not an improvement) undo Tags: Manual revert Mobile edit Mobile web edit
curprev 15:3615:36, 23 October 2024 Khethan talk contribs m 184,297 bytes +398 No edit summary undo Tags: Reverted Visual edit

curprev 13:3813:38, 16 October 2024 Anoopkritagya talk contribs m 183,899 bytes −1 No edit summary undo
curprev 13:3813:38, 16 October 2024 Anoopkritagya talk contribs m 183,900 bytes +4 No edit summary undo

curprev 22:1822:18, 12 October 2024 Alenoach talk contribs 183,896 bytes −1,506 Copyedited a paragraph and removed the next one, which was less directly relevant undo Tag: Visual edit

curprev 12:0612:06, 5 October 2024 MrOllie talk contribs 185,402 bytes −626 I have to agree, this does look like a refspam campaign and it is undue coverage of a primary source undo Tag: Manual revert
curprev 12:0512:05, 5 October 2024 WeyerStudentOfAgrippa talk contribs 186,028 bytes +43 →Applications: ref link undo Tags: Reverted Mobile edit Mobile app edit Android app edit App section source
curprev 12:0212:02, 5 October 2024 WeyerStudentOfAgrippa talk contribs 185,985 bytes +583 Undid revision 1249529206 by Janhrach (talk) Why? undo Tags: Undo Reverted Mobile edit Mobile app edit Android app edit App undo
curprev 11:4911:49, 5 October 2024 Janhrach talk contribs 185,402 bytes −583 preventively reverting an edit from 194.247.67.196/30 – possibly a spam campaign undo Tags: Undo Reverted

curprev 05:3005:30, 24 September 2024 Citation bot talk contribs 185,985 bytes +2 Alter: journal, pages. Added date. Removed parameters. Formatted dashes. Some additions/deletions were parameter name changes. | Use this bot. Report bugs. | Suggested by Jay8g | #UCB_toolbar undo

curprev 12:2412:24, 23 September 2024 WeyerStudentOfAgrippa talk contribs 185,983 bytes −46 Undid revision 1247181900 by Samba599 (talk) Unnecessary specification undo Tags: Undo Mobile edit Mobile app edit Android app edit App undo
curprev 05:3905:39, 23 September 2024 Perceptron599 talk contribs 186,029 bytes +46 Specify short description undo Tags: Reverted Mobile edit Mobile web edit

curprev 14:1214:12, 20 September 2024 MrOllie talk contribs 185,983 bytes −837 Restored revision 1246380436 by 194.247.67.198 (talk): Seems off topic and undue undo Tags: Twinkle Undo
curprev 05:0505:05, 20 September 2024 Cyanseeker talk contribs 186,820 bytes +837 edit the page, add more info and references undo Tags: Reverted Visual edit

curprev 16:1216:12, 18 September 2024 194.247.67.198 talk 185,983 bytes +583 No edit summary undo Tag: Reverted

curprev 17:2917:29, 14 September 2024 Speedboys talk contribs 184,090 bytes +471 →Before 1980: Already in 1948, Alan Turing produced work "related to artificial evolution and learning RNNs" that was not published in his lifetime. undo
curprev 17:0717:07, 14 September 2024 Speedboys talk contribs 183,619 bytes +1,596 →Before 1980: Elman networks and Jordan networks are mentioned, but not the origins of RNNs. Resurrecting deleted text of 6 Aug 2024: In the 1920s, Wilhelm Lenz and Ernst Ising created and analyzed the Ising model, the first RNN architecture. It did not learn. In 1972, Shun'ichi Amari made it adaptive. This became the foundation of the Hopfield network and the Boltzmann Machine and many other recurrent models. undo
curprev 16:4516:45, 14 September 2024 Speedboys talk contribs 182,023 bytes −493 →Deep learning revolution: GANs are based on the 1991 curiosity principle. Highway nets (May 2015) were published 7 months before ResNets (Dec 2015). Deleted "concurrently." ResNet is like an open-gated Highway Net. undo
curprev 16:2716:27, 14 September 2024 Speedboys talk contribs 182,516 bytes +2,728 →1980s-2000s: Corrections based on deleted text of 6 Aug 2024: in 1991, the pre-trained history compressor with knowledge distillation was proposed not by Sepp Hochreiter but by his advisor Juergen Schmidhuber, who also published the GAN principle in 1991. Fixed URLs in references. undo

curprev 17:1617:16, 13 September 2024 Speedboys talk contribs 179,788 bytes +343 →1980s-2000s: Alex Waibel's 1987 reference copied from Convolutional Neural Network. Temporal order of CNN applications corrected: Wei Zhang et al. 1988, Yann LeCun et al. 1989, CNN optical hardware by Zhang in 1990. undo
curprev 16:5616:56, 13 September 2024 Speedboys talk contribs 179,445 bytes +307 →History: 1979 reference: Fukushima's CNN architecture moved from the 1980s to the 1970s. undo
curprev 16:4516:45, 13 September 2024 Speedboys talk contribs 179,138 bytes +17 →History: Kunihiko Fukushima's ReLU moved from the 1980s to the 1960s. undo

curprev 17:0317:03, 10 September 2024 Speedboys talk contribs 179,121 bytes +360 →Before 1980: Alexey Grigorevich Ivakhnenko and Valentin Lapa in 1965: layer by layer training through regression analysis, superfluous hidden units pruned using a separate validation set, first deep networks with multiplicative units or "gates" undo
curprev 16:0316:03, 10 September 2024 Speedboys talk contribs 178,761 bytes +48 →Before 1980: Frank Rosenblatt (1962) cites an earlier network by R. D. Joseph (1960) "functionally equivalent to a variation of" his four-layer system "with adaptive preterminal networks." Rosenblatt's book mentions Joseph over 30 times. Should one consider Joseph (1960) as the originator of adaptive multilayer perceptrons? Unfortunately, the learning algorithm was not a functional one, and fell into oblivion. undo

curprev 23:0423:04, 5 September 2024 Cosmia Nebula talk contribs 178,713 bytes +15 →Deep learning revolution: link to vgg undo Tag: Visual edit

curprev 03:2403:24, 3 September 2024 MusubiToTheMax talk contribs 178,698 bytes +184 List additional deep learning-based architectures. undo Tag: Visual edit
curprev 03:1603:16, 3 September 2024 MusubiToTheMax talk contribs 178,514 bytes +20 No edit summary undo Tag: Visual edit
curprev 03:1403:14, 3 September 2024 MusubiToTheMax talk contribs 178,494 bytes +229 Introduce the biological origin of traditional deep learning research. undo Tag: Visual edit

curprev 14:5014:50, 2 September 2024 DariusMarc talk contribs 178,265 bytes +4 Grammar edit undo Tags: Visual edit Mobile edit Mobile web edit
curprev 14:4514:45, 2 September 2024 DariusMarc talk contribs m 178,261 bytes +11 Grammar edit undo Tags: Visual edit Mobile edit Mobile web edit

curprev 14:0814:08, 1 September 2024 ProcrastinatingReader talk contribs 178,250 bytes −32 clarify lead: all of these architectures are types of neural networks, whereas the current prose seems to suggest they are different to a neural net. undo Tag: Visual edit

curprev 09:4709:47, 30 August 2024 178.115.59.5 talk 178,282 bytes 0 typo corrected undo

curprev 10:5910:59, 29 August 2024 Giantflightlessbirds talk contribs 178,282 bytes +71 Improving caption undo Tag: Visual edit
curprev 10:5710:57, 29 August 2024 Giantflightlessbirds talk contribs 178,211 bytes +148 Adding video clip undo Tag: Visual edit

curprev 08:2908:29, 21 August 2024 Ednabrenze talk contribs m 178,063 bytes +6 Reverted 1 edit by 192.248.8.114 (talk) to last revision by Conan undo Tags: Twinkle Undo

21 November 2024

16 November 2024

14 November 2024

11 November 2024

10 November 2024

5 November 2024

3 November 2024

2 November 2024

23 October 2024

16 October 2024

12 October 2024

5 October 2024

24 September 2024

23 September 2024

20 September 2024

18 September 2024

15 September 2024

14 September 2024

13 September 2024

10 September 2024

5 September 2024

3 September 2024

2 September 2024

1 September 2024

30 August 2024

29 August 2024

21 August 2024