1652:(2009). Unfortunately, Nilsson is not a very good source because he writes things such as, "Rumelhart, Geoffrey E. Hinton, and Ronald J. Williams (1985), introduced a new technique, called back propagation," without mentioning the true inventors of backpropagation. He also writes that "the physicist John J. Hopfield" invented the Hopfield network, without citing Amari who published it 10 years earlier. Neither Nilsson nor the even older surveys you mention cite Ivakhnenko who started deep learning in 1965. Isn't that a rather US-centric non-NPOV here? Most of the community learned about the true pioneers from JS' much more meticulous surveys which you critisize. See my previous message. His 2015 survey lists nearly 900 references, his 2022 update over 500, adding stuff that has become important since 2015 (this is not about citations). Could it be that you have a tiny little bit of non-NPOV of your own? Maybe we all have. But then let's find a consensus. You call "unnormalized linear Transformers" a "great rhetorical trick." Why? Unlike older networks you mention, they do have linearized attention and scale linearly. The terminology "linear Transformer" is due to Katharopoulos et al. (2020), but JS had the machinery already in 1991, as was pointed out in 2021 (see reverted edits). You also claim that early NN architectures (McCulloch and Pitts, 1943) did learn. I know the paper, and couldn't find a working learning algorithm in it. Could you? Note that Gauss and Legendre had a working learning algorithm for linear neural nets over 200 years ago, another must-cite. Anyway, I'll try to follow the recommendations on this talk page and go step by step from now on, in line with
1527:, who introduced residual connections or "constant error flow," the "roots of LSTM / Highway Nets / ResNets." Anyway, thanks for toning that down. You deleted important references to JS' 1991 work on self-supervised pre-training, neural network distillation, GANs, and unnormalized linear Transformers; I tried to undo this on 16 Sept 2024. Regardless of the plagiarism disputes, one cannot deny that this work predates GH/YB and colleagues by a long way. In the interest of historical accuracy, I still propose to revert the revert of my 10 edits, and continue from there. In the future, we could strive to explicitly mention details of the priority disputes between these important people, trying to represent all sides in an NPOV way. I bet you could contribute a lot here. What do you think?
1430:. 2. It relies much on Schmidhuber's history, especially "Annotated History of Machine Learning", and Schmidhuber is an unreliable propagandist who bitterly contests priority with everyone else. He aims to show that modern deep learning is mostly originated by his team, or others like Lapa and Fukushima etc, specifically *not* LeCun, Bengio, etc. You can press ctrl+f and type "did not" and find phrases like "This work did not cite the earlier LSTM" "which the authors did not cite" "extremely unfair that Schmidhuber did not get the Turing award"...
1497:(JS,GH,YB,YL) is the very explicit 2023 report which to my knowledge has not been challenged. The most comprehensive surveys of the field are those published by JS in 2015 and 2022, with over 1000 references in total; wouldn't you agree? They really credit the deep learning pioneers, unlike the surveys of GH/YB/YL. I'd say that JS has become a bit like the chief historian of the field, with the handicap that he is part of it (as you wrote: non-NPOV?). Anyway, without his surveys, many practitioners would not even know the following facts:
301:
280:
911:
890:
1795:. I propose to replace the section "Neural network winter" by the section "Deep learning breakthroughs in the 1960s and 1970s" below. Why? The US "neural network winter" (if any) did not affect Ukraine and Japan, where fundamental breakthroughs occurred in the 1960s and 1970s: Ivakhnenko (1965), Amari (1967), Fukushima (1969, 1979). The Kohonen maps (1980s) should be moved to a later section. I should point out that much of the proposed text is based on older resurrected text written by other editors.
1545:"Annotated History of Modern AI and Deep Learning" was cited about 63 times, while "Deep learning in neural networks: An overview" was cited over 22k times. It is clear why if you compare the two. The "Deep learning in neural networks" is a mostly neutral work (if uncommonly citation-heavy), while the "Annotated History" is extremely polemical (even beginning the essay with a giant collage of people's faces and their achievements, recalling to mind the book covers from those 17th century
247:
1874:(1965). They regarded it as a form of polynomial regression, or a generalization of Rosenblatt's perceptron. A 1971 paper described a deep network with eight layers trained by this method, which is based on layer by layer training through regression analysis. Superfluous hidden units are pruned using a separate validation set. Since the activation functions of the nodes are Kolmogorov-Gabor polynomials, these were also the first deep networks with multiplicative units or "gates."
1152:
1336:
1380:(whose efforts I appreciate) tried to compress the text‎. This massive edit has remained unchallenged until now. I also fixed links in some of the old references, added a few new ones (both primary and secondary sources), corrected many little errors, and tried to streamline some of the explanations. IMO these edits restored important parts and further improved the history section of the article, although a lot remains to be done. Now I kindly ask
2115:, Holland, Habit and Duda (1956). The perceptron raised public excitement for research in Artificial Neural Networks, causing the US government to drastically increase funding. This contributed to "the Golden Age of AI" fueled by the optimistic claims made by computer scientists regarding the ability of perceptrons to emulate human intelligence. The first perceptrons did not have adaptive hidden units. However, Joseph (1960) also discussed
1403:
for being the one to pioneer various aspect. So I'm not open to reinstating that whole linked bundle including those. Why not just slow down and put those things back in at a pace where they can be reviewed? And the the ones that are are a reach (transferring or assigning credit for invention) take to talk first. You are most familiar with the details of your edits and are in the best position to know those. Sincerely,
1068:
1050:
646:
390:
1004:
979:
369:
1717:: The original version of the "Early Work" section has a very good and accessible overview of the field, and it wikilinks related subjects in a rather fluid way. I think your version of that section, by going deep into crediting and describing a single primary sources on each topic, just doesn't work. As noted above, doing such a fine-grained step-by-step review of primary works of the history is better for the
1376:. He reverted and wrote, "you are doing massive reassignment of credit for Neural Networks based on your interpretation of their work and primary sources and deleting secondary sourced assignments. Please slow down and take such major reassignments to talk first." So here. Please note that most of my edits are not novel! They resurrect important old references deleted on 7 August 2024 in a major edit when
569:
548:
207:
238:
1814:. Also, the extraordinary claim that CNNs "began with" Neocognitron -- that makes it sound like Neocognitron leveraged the key insight of CNNs which was to reduce the number of weights by using the same weights, effectively, for each pixel, running the kernel(s) across the image. From my limited understand, that is not the case with Neocognitron. The article dedicated to
1698:, you say, "do not reply," but I must: that's not a learning algorithm. Sure, McCulloch and Pitts' Turing-equivalent model (1943) is powerful enough to implement any learning algorithm, but they don't describe one: no goal, no objective function to maximise, no explicit learning algorithm. Otherwise it would be known as the famous McCulloch and Pitts learning algorithm.
484:
466:
1296:
2051:'s work on perceptrons (1958). My third party source is R.D. Joseph (1960) who mentions an even earlier perceptron-like device by Farley and Clark: "Farley and Clark of MIT Lincoln Laboratory actually preceded Rosenblatt in the development of a perceptron-like device." I am also copying additional Farley and Clark references (1954) from
1836:, thanks! I agree, I must delete the phrase "of course" in the draft below. I just did. Regarding the Neocognitron: that's another article that must be corrected, because the Neocognitron CNN did have "massive weight replication," and a third party reference on this is section 5.4 of the 2015 survey. I added this to the draft below.
1580:). Physicists don't cite Newton when they write new papers. They don't even cite Schrödinger. Mathematicians don't cite Gauss-Legendre for least squares. They have a vague feeling that they did something about least squares, and that's enough. It is no serious problem. Historians will do all that detailed credit assignment later.
1078:
1587:, there were several ways to arrive at RNN. One route goes through neuroanatomy. The very first McCulloch and Pitts 1943 paper already had RNN, Hebbian learning, and universality. They had no idea of Ising, nor did they need to, because they got the idea from neuroscientists like Lorente de No. Hopfield cited Amari, btw.
1611:
But I am tired of battling over the historical minutae. Misunderstanding history doesn't hurt the practitioners, because ideas are cheap, and are rediscovered all the time (see: Schmidhuber's long list of grievances), so not citing earlier works is not an issue. This is tiring, and I'm signing out of
1552:
As for the "very explicit 2023 report", it is... not a report. It is the most non-NPOV thing I have seen (beginning the entire report with a damned caricature comic?) and I do not want to read it. He is not the chief historian. He is the chief propagandist. If you want better history of deep learning
1437:
His campaign reached levels of absurdity when he claimed that Amari (1972)'s RNN is "based on the (uncited) Lenz-Ising recurrent architecture". If you can call the Ising model as "The first non-learning recurrent NN architecture", then I can call the heat death of the universe "The first non-evolving
1453:
As a general principle, if I can avoid quoting
Schmidhuber, I must, because Schmidhuber is extremely non-NPOV. I had removed almost all citations to his Annotated History except those that genuinely cannot be found anywhere else. For example, I kept all citations to that paper about Amari and Saito,
1595:
We suppose that some axonal terminations cannot at first excite the succeeding neuron; but if at any time the neuron fires, and the axonal terminations are simultaneously excited, they become synapses of the ordinary kind, henceforth capable of exciting the neuron. That is
Hebbian learning (6 years
1724:
I don't know the sources on this at all, but I just lend support to editors above for at least this section, on prose, accessibility, and accuracy in a broader conceptual sense, you should not restore your edits wholesale. (I know it's a lot of work, as writing good accessible prose is super hard,
1449:
J. Schmidhuber (AI Blog, 02/20/2020, updated 2021, 2022). The 2010s: Our Decade of Deep
Learning / Outlook on the 2020s. The recent decade's most important developments and industrial applications based on the AI of Schmidhuber's team, with an outlook on the 2020s, also addressing privacy and data
1402:
Recapping my response from our conversation at my talk page: Thanks for your work and your post. The series of rapid fire edits ended up being entangled where they an't be reviewed/ potentially reverted separately. In that bundle were several which IMO pretty creatively shifted/assigned credit
1541:
The most important issue is that any citation to
Schmidhuber's blog posts, essays, and "Annotated History" invariably taints a Knowledge (XXG) page with non-NPOV. Before all those details, this is the main problem with citing Schmidhuber. Citing earlier works is fine, but it is *NOT* fine to cite
1522:
had backpropagation (reverse mode of auto-diff) in 1970. G.M. Ostrovski republished this in 1971. Henry J. Kelley already had a precursor in 1960. Tow centuries ago, Gauss and
Legendre had the method of least squares which is exactly what's now called a linear neural network (only the name has
1607:
You can find it if you ctrl+f "learn" in the paper. A little later they showed that
Hebbian learning in a feedforward network is equivalent to an RNN by unrolling that RNN in time. ("THEOREM VII. Alterable synapses can be replaced by circles.", and Figure 1.i. The dashed line is the learnable
1433:
It is even more revealing if you ctrl+f on "Hinton". More than half of the citations to Hinton are followed by "Very similar to ", "although this type of deep learning dates back to
Schmidhuber's work of 1991", "does not mention the pioneering works", "The authors did not cite Schmidhuber's
1572:
trying to figure out if attention really is necessary (for example, "Sparse MLP for image recognition: Is self-attention really necessary?" or MLP-mixers). Does that mean feedforward networks are "attentionless
Transformers"? Or can I just put Rosenblatt into the Transformer page's history
667:
1523:
changed). If JS is non-NPOV (as you write), then how non-NPOV are GH/YB/YL who do not cite any of this? You blasted JS' quote, "one of the most important documents in the history of machine learning," which actually refers to the 1991 diploma thesis of his student
1445:, and it came straight from his "Annotated History of Machine Learning". I removed all examples of this phrase in Knowledge (XXG) except in his own page (he is entitled to his own opinions). In fact, the entire paper is scattered with such propagandistic sentences:
2107:. R. D. Joseph (1960) mentions an even earlier perceptron-like device by Farley and Clark: "Farley and Clark of MIT Lincoln Laboratory actually preceded Rosenblatt in the development of a perceptron-like device." However, "they dropped the subject." Farley and
1559:
Mikel
Olazaran, A Historical Sociology of Neural Network Research (PhD dissertation, Department of Sociology, University of Edinburgh, 1991); Olazaran, `A Sociological History of the Neural Network Controversy', Advances in Computers, Vol. 37 (1993),
1163:
190:
2119:
with an adaptive hidden layer. Rosenblatt (1962) cited and adopted these ideas, also crediting work by H. D. Block and B. W. Knight. Unfortunately, these early efforts did not lead to a working learning algorithm for hidden units, i.e.,
153:
1590:
Schmidhuber is not reliable by the way. I just checked his "Deep learning in neural networks" and immediately saw an error: "Early NN architectures (McCulloch and Pitts, 1943) did not learn." In fact, it stated right here in the
1458:
H. Saito (1967). Master's thesis, Graduate School of
Engineering, Kyushu University, Japan. Implementation of Amari's 1967 stochastic gradient descent method for multilayer perceptrons. (S. Amari, personal communication, 2021.)
1967:, thanks for encouraging me to resume the traditional way of editing. I tried to address the comments of the other users. Now I want to edit the article accordingly, and go step by step from there, as you suggested.
1745:
is sufficiently against the content that you had added, that it should not be reverted back in the same form. Please follow the advice of other editors above, and propose specific text to add back, here in talk.
1513:
had Hopfield networks 10 years before Hopfield, plus a sequence-learning generalization (the "dynamic RNN" as opposed to the "equilibrium RNN" you mentioned), all using the must-cite Ising architecture (1925).
1946:
basis and (just) seek prior consensus on the controversial ones such as assigning / implying credit to individuals. A slower pace with smaller edits makes it reviewable and so is itself a review process.
1454:
because 1. H. Saito is so extremely obscure that if we don't cite Schmidhuber on this, we have no citation for this. 2. I can at least trust that he didn't make up the "personal communication" with Amari.
2073:
I don't have the specialized knowledge to fully evaluate it but overall it looks pretty good to me. Mentions people in the context of early developments without being heavy on claim/credit type wording.
961:
1438:
model of Darwinian evolution". The entire point of RNN is that it is dynamic, and the entire point of the Ising model is that it is about thermal equilibrium at a point where all dynamics has *stopped*.
3069:
1212:
1257:
1252:
1232:
1227:
1202:
1262:
1247:
1222:
1217:
1197:
1192:
691:
831:
1923:(1969), who emphasized that basic perceptrons were incapable of processing the exclusive-or circuit. This insight was irrelevant for the deep networks of Ivakhnenko (1965) and Amari (1967).
1267:
1237:
2969:
1441:
As one example, the phrase "one of the most important documents in the history of machine learning" used to appear several times all across Knowledge (XXG), and is an obvious violation of
1242:
1207:
1187:
44:
1725:
but the hardest part -- finding and understanding the source material -- you've already done and banked, so you should definitely keep up editing on this and the many related articles.)
147:
1671:
but if at any time the neuron fires, and the axonal terminations are simultaneously excited, they become synapses of the ordinary kind, henceforth capable of exciting the neuron
748:
686:
1677:
Again. Gauss or Legendre are not a must cite. I had read hundreds of math and CS papers and never had I needed to know who or what or at what paper least squares was proposed.
1576:
Ising architecture (1925) is NOT a must-cite. It is not even a neural network architecture (though you can really retroactively call an "architecture", but historians call it
619:
1549:). It is very strange that you would combine them in one sentence and say "with over 1000 references in total" as if they have nearly the same order of magnitude in citation.
2029:
on 7 August: JS' 1991 work on self-supervised pre-training, neural network distillation, GANs, and unnormalized linear Transformers, using the improved text of 24 September.
2959:
3024:
3014:
1568:
Calling something "unnormalized linear Transformers" is a great rhetorical trick, and I can call feedforward networks "attentionless Transformers". I am serious. People
609:
524:
194:
530:
3054:
1124:
3029:
1130:
585:
251:
2974:
448:
79:
2954:
1616:, you seem passionate about history. It would be good to try to actually read the primary sources, do not trust Schmidhuber's interpretation, and read some
351:
3039:
951:
3064:
3019:
2999:
2868:
Rochester, N.; J.H. Holland; L.H. Habit; W.L. Duda (1956). "Tests on a cell assembly theory of the action of the brain, using a large digital computer".
793:
438:
1010:
984:
500:
2984:
1481:
alias "pony in a strange land," thanks for your reply! I see where you are coming from. The best reference to the mentioned priority disputes between
341:
2650:
Fukushima, K. (1980). "Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position".
632:
576:
553:
3059:
3044:
2112:
1100:
927:
85:
2964:
1648:, thanks! I am always going to the source when I find something of interest in a survey. You condemn JS and recommend alternative surveys such as
767:
414:
3009:
2989:
739:
317:
168:
2908:
2597:
2346:
2052:
1427:
856:
491:
471:
135:
3049:
3034:
30:
720:
1893:
to classify non-linearily separable pattern classes. Subsequent developments in hardware and hyperparameter tunings have made end-to-end
2994:
2141:
1091:
1055:
918:
895:
2979:
397:
374:
99:
1373:
24:
2111:(1954) also used computational machines to simulate a Hebbian network. Other neural network computational machines were created by
1318:
308:
285:
104:
20:
2613:
Fukushima, K. (1979). "Neural network model for a mechanism of pattern recognition unaffected by shift in position—Neocognitron".
2413:
1577:
1350:
129:
1612:
the debate. A word of advice: If you must use Schmidhuber's history, go directly to the source. Do not use his interpretation. @
74:
3004:
2949:
812:
777:
658:
260:
198:
2142:"How 3 Turing Awardees Republished Key Methods and Ideas Whose Creators They Failed to Credit. Technical Report IDSIA-23-23"
701:
125:
65:
1863:
822:
584:
related articles on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
1927:
1741:
Speedboys, whatever else may be the case, I don't think that you should "revert the revert... and continue from there."
2047:, my next proposed edit (see draft below based on the reverted edit of 15 September) is about important work predating
1342:
175:
2700:
Rosenblatt, F. (1958). "The Perceptron: A Probabilistic Model For Information Storage And Organization in the Brain".
1905:
1894:
1882:
787:
2522:
Sonoda, Sho; Murata, Noboru (2017). "Neural network with unbounded activation functions is universal approximator".
1889:. In computer experiments conducted by Amari's student Saito, a five layer MLP with two modifiable layers learned
1718:
1388:
who seem to know a lot about the subject: please review the details once more and revert the revert! Best regards,
1157:
206:
185:
109:
1674:
That is a learning algorithm. Ignore it if you must. As i said. I'm tired of fighting over this priority dispute.
1563:
Anderson, James A., and Edward Rosenfeld, eds. Talking nets: An oral history of neural networks. MiT Press, 2000.
1346:
1317:
For more information about external reviews of Knowledge (XXG) articles and about this review in particular, see
849:
1170:
217:
2104:
1890:
1584:
758:
266:
141:
1685:
1635:
1464:
1015:
989:
2709:
2566:
Ramachandran, Prajit; Barret, Zoph; Quoc, V. Le (October 16, 2017). "Searching for Activation Functions".
2495:
Fukushima, K. (1969). "Visual feature extraction by a multilayered network of analog threshold elements".
2116:
2056:
1823:
410:
1792:
1774:
1742:
1653:
55:
2896:
1878:
1099:
on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
926:
on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
499:
on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
413:
on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
316:
on Knowledge (XXG). If you would like to participate, please visit the project page, where you can join
2782:
Olazaran, Mikel (1996). "A Sociological Study of the Official History of the Perceptrons Controversy".
2234:
1482:
300:
279:
70:
910:
889:
2828:
Contributions to Perceptron Theory, Cornell Aeronautical Laboratory Report No. VG-11 96--G-7, Buffalo
2274:
1751:
2713:
1942:
Others may think differently, but I'd be happy if you just made smaller edits at a slower pace on a
677:
237:
2081:
2064:
2016:
2002:
1986:
1972:
1954:
1909:
1841:
1800:
1782:
1730:
1661:
1532:
1410:
1393:
161:
1620:
histories than his history. Other than the references I gave above, I can also recommend this one
1518:
had early unpublished work (1948) with "ideas related to artificial evolution and learning RNNs."
2806:
2799:
2733:
2674:
2633:
2567:
2549:
2531:
2319:
2297:
2238:
2206:
2181:
2026:
1935:
1901:
1695:
1681:
1645:
1631:
1506:
1478:
1460:
1385:
1377:
1176:
222:
2363:
2085:
2068:
2020:
2006:
1990:
1976:
1958:
1845:
1827:
1804:
1786:
1773:, thanks. I'll try to follow your recommendations and go step by step from now on, in line with
1755:
1734:
1689:
1665:
1639:
1536:
1468:
1414:
1397:
1930:(CNNs) with convolutional layers and downsampling layers and weight replication began with the
1596:
before Hebb's 1949 book, but... Hebbian learning was an immediately obvious idea once you have
1556:
The quest for artificial intelligence: a history of ideas and achievements, by Nilsson, Nils J.
1434:
original"... You can try the same exercise by ctrl+f on "LeCun" and "Bengio". It is very funny.
2905:
2841:
Farley, B.G.; W.A. Clark (1954). "Simulation of Self-Organizing Systems by Digital Computer".
2726:
2667:
2626:
2594:
2343:
2314:
Bengio, Yoshua; LeCun, Yann; Hinton, Geoffrey (2021). "Turing Lecture: Deep Learning for AI".
2290:
2199:
1981:
Done. Now the section on CNNs must be adjusted a bit, to reflect the beginnings in the 1970s.
1867:
1833:
1819:
1649:
1498:
1083:
51:
2145:
1583:
Ising architecture is NOT a must-cite even in the 1970s, because, as you might notice in the
1442:
1174:
803:
221:
2924:
2877:
2850:
2791:
2718:
2659:
2618:
2541:
2504:
2473:
2453:
2405:
2375:
2282:
2191:
2096:
2048:
1886:
1519:
1510:
1502:
1304:
1280:
1172:
729:
581:
219:
1943:
1426:
My main concern with the page were 1. It had too many details that probably should go into
2437:
2108:
1770:
1747:
1601:
1524:
1486:
2278:
2055:. Finally, Frank Rosenblatt also cites Joseph's work (1960) on adaptive hidden units in
2103:, one of the first implemented artificial neural networks, funded by the United States
2060:
2044:
2012:
1982:
1968:
1964:
1920:
1837:
1796:
1778:
1766:
1726:
1657:
1613:
1597:
1528:
1421:
1389:
1381:
1369:
645:
2259:
1810:
Not bad, but there is some anti-U.S. tone. E.g. the phrase "of course" falls afoul of
668:
Requested articles/Applied arts and sciences/Computer science, computing, and Internet
2943:
2677:
2636:
2379:
2121:
1916:
1859:
1858:
Fundamental research was conducted on ANNs in the 1960s and 1970s. The first working
1546:
1490:
2809:
2736:
2552:
2209:
2767:
Rosenblatt, Frank (1957). "The Perceptron—a perceiving and recognizing automaton".
2753:
Beyond Regression: New Tools for Prediction and Analysis in the Behavioral Sciences
2322:
2300:
2025:
I waited for a day, as suggested. The latest edit resurrects references deleted by
1931:
1912:. The rectifier has become the most popular activation function for deep learning.
1815:
1811:
1627:
496:
2394:
2751:
2588:
2337:
2195:
1515:
1067:
1049:
2795:
2545:
1003:
978:
389:
368:
2458:
2441:
2409:
2100:
1494:
1295:
1096:
1073:
923:
2881:
2854:
2508:
1915:
Nevertheless, research stagnated in the United States following the work of
1818:
uses the more accurate phrase of that CNNs were "inspired by" Neocognitron.
710:
406:
2729:
2293:
2202:
568:
547:
2670:
2629:
2172:
Schmidhuber, J. (2015). "Deep Learning in Neural Networks: An Overview".
402:
313:
2286:
2663:
2622:
1871:
483:
465:
2802:
2722:
2364:"Heuristic self-organization in problems of engineering cybernetics"
2904:(3rd ed.). United States of America: Pearson Education. pp. 16–28.
2572:
2536:
2243:
2011:
I'll wait a bit, as you suggested. But there is still a lot to do.
1866:, a method to train arbitrarily deep neural networks, published by
2186:
1364:
History section: request to approve edits of 15-16 September 2024
2690:
Haykin (2008) Neural Networks and Learning Machines, 3rd edition
1995:
I'd suggest smaller edits and waiting a day or 2 between them.
1330:
1290:
1177:
786:
Find pictures for the biographies of computer scientists (see
231:
223:
15:
2237:(2022). "Annotated History of Modern AI and Deep Learning".
1791:
Dear all, please review my first proposed edit in line with
1505:
had Deep Learning by Stochastic Gradient Descent in 1967.
1623:
1621:
1713:
2590:
Perceptrons: An Introduction to Computational Geometry
2258:
LeCun, Yann; Bengio, Yoshua; Hinton, Geoffrey (2015).
1341:
On 8 March 2024, it was proposed that this article be
160:
3070:
Externally peer reviewed articles by Nature (journal)
1509:
had ReLUs in 1969, and the CNN architecture in 1979.
2970:
Knowledge (XXG) level-5 vital articles in Technology
2497:
IEEE Transactions on Systems Science and Cybernetics
2091:
Early work on perceptrons and multilayer perceptrons
1542:
Schmidhuber's interpretation of these earlier works.
1095:, a collaborative effort to improve the coverage of
922:, a collaborative effort to improve the coverage of
580:, a collaborative effort to improve the coverage of
495:, a collaborative effort to improve the coverage of
401:, a collaborative effort to improve the coverage of
312:, a collaborative effort to improve the coverage of
2476:(1967). "A theory of adaptive pattern classifier".
174:
2402:IEEE Transactions on Systems, Man, and Cybernetics
1854:Deep learning breakthroughs in the 1960s and 1970s
1630:on a specific problem in neural network research.
1553:I would rather recommend something else, such as:
1129:This article has not yet received a rating on the
692:Computer science articles needing expert attention
529:This article has not yet received a rating on the
1938:in 1979, though not trained by backpropagation.
1013:, a project which is currently considered to be
33:for general discussion of the article's subject.
1501:had a working deep learning algorithm in 1965.
832:WikiProject Computer science/Unreferenced BLPs
2821:
2819:
1025:Knowledge (XXG):WikiProject Cognitive science
8:
2960:Knowledge (XXG) vital articles in Technology
594:Knowledge (XXG):WikiProject Computer science
2524:Applied and Computational Harmonic Analysis
2229:
2227:
2225:
2223:
2221:
2219:
2167:
2165:
2163:
1897:the currently dominant training technique.
749:Computer science articles without infoboxes
687:Computer science articles needing attention
1146:
1044:
973:
884:
653:Here are some tasks awaiting attention:
627:
542:
460:
363:
274:
2898:Artificial Intelligence A Modern Approach
2712:
2571:
2535:
2457:
2242:
2185:
2140:Schmidhuber, Juergen (14 December 2023).
3025:Top-importance Computer science articles
3015:Unknown-importance neuroscience articles
2587:Minsky, Marvin; Papert, Seymour (1969).
509:Knowledge (XXG):WikiProject Neuroscience
2336:Ivakhnenko, A. G.; Lapa, V. G. (1967).
2132:
1046:
975:
886:
544:
462:
365:
276:
235:
3055:Unknown-importance psychology articles
2955:Knowledge (XXG) level-5 vital articles
2895:Russel, Stuart; Norvig, Peter (2010).
2870:IRE Transactions on Information Theory
2843:IRE Transactions on Information Theory
2395:"Polynomial theory of complex systems"
2339:Cybernetics and Forecasting Techniques
1109:Knowledge (XXG):WikiProject Psychology
1028:Template:WikiProject Cognitive science
936:Knowledge (XXG):WikiProject Statistics
3030:WikiProject Computer science articles
2446:The Annals of Mathematical Statistics
2053:History_of_artificial_neural_networks
1428:History of artificial neural networks
597:Template:WikiProject Computer science
423:Knowledge (XXG):WikiProject Computing
7:
2975:C-Class vital articles in Technology
2144:. IDSIA, Switzerland. Archived from
1372:, on 15-16 September 2024, I edited
1089:This article is within the scope of
1009:This article is within the scope of
916:This article is within the scope of
574:This article is within the scope of
489:This article is within the scope of
395:This article is within the scope of
326:Knowledge (XXG):WikiProject Robotics
306:This article is within the scope of
2442:"A Stochastic Approximation Method"
2342:. American Elsevier Publishing Co.
265:It is of interest to the following
23:for discussing improvements to the
3040:Mid-importance Statistics articles
2771:. Cornell Aeronautical Laboratory.
768:Timeline of computing 2020–present
14:
3065:Externally peer reviewed articles
3020:C-Class Computer science articles
3000:Top-importance Computing articles
1374:Neural network (machine learning)
794:Computing articles needing images
512:Template:WikiProject Neuroscience
50:New to Knowledge (XXG)? Welcome!
25:Neural network (machine learning)
2985:Top-importance Robotics articles
1926:Deep learning architectures for
1714:2024-09-16 diff under discussion
1334:
1294:
1150:
1076:
1066:
1048:
1002:
977:
909:
888:
644:
567:
546:
482:
464:
388:
367:
299:
278:
245:
236:
205:
45:Click here to start a new topic.
3060:WikiProject Psychology articles
3045:WikiProject Statistics articles
2419:from the original on 2017-08-29
2362:Ivakhnenko, A.G. (March 1970).
1112:Template:WikiProject Psychology
956:This article has been rated as
939:Template:WikiProject Statistics
614:This article has been rated as
443:This article has been rated as
346:This article has been rated as
2965:C-Class level-5 vital articles
2086:01:48, 22 September 2024 (UTC)
2069:11:19, 21 September 2024 (UTC)
2021:13:25, 20 September 2024 (UTC)
2007:13:05, 20 September 2024 (UTC)
1991:11:08, 20 September 2024 (UTC)
1977:10:29, 20 September 2024 (UTC)
1959:13:13, 19 September 2024 (UTC)
1846:10:29, 20 September 2024 (UTC)
1828:13:22, 19 September 2024 (UTC)
1805:12:17, 19 September 2024 (UTC)
1787:11:58, 19 September 2024 (UTC)
1756:18:58, 18 September 2024 (UTC)
1735:19:30, 18 September 2024 (UTC)
1690:21:03, 19 September 2024 (UTC)
1666:11:58, 19 September 2024 (UTC)
1640:22:07, 18 September 2024 (UTC)
1537:14:21, 18 September 2024 (UTC)
1469:01:36, 18 September 2024 (UTC)
1415:00:35, 18 September 2024 (UTC)
1398:21:24, 17 September 2024 (UTC)
1314:It was found to have 7 errors.
426:Template:WikiProject Computing
1:
3010:C-Class neuroscience articles
2990:WikiProject Robotics articles
1928:convolutional neural networks
1864:Group method of data handling
1301:This article was reviewed by
1103:and see a list of open tasks.
1011:WikiProject Cognitive science
930:and see a list of open tasks.
848:Tag all relevant articles in
588:and see a list of open tasks.
503:and see a list of open tasks.
417:and see a list of open tasks.
329:Template:WikiProject Robotics
320:and see a list of open tasks.
42:Put new text under old text.
2380:10.1016/0005-1098(70)90092-0
2196:10.1016/j.neunet.2014.09.003
857:WikiProject Computer science
633:WikiProject Computer science
577:WikiProject Computer science
3050:C-Class psychology articles
3035:C-Class Statistics articles
2929:Principles of Neurodynamics
2393:Ivakhnenko, Alexey (1971).
1895:stochastic gradient descent
1883:stochastic gradient descent
788:List of computer scientists
3086:
2995:C-Class Computing articles
2796:10.1177/030631296026003005
2546:10.1016/j.acha.2015.12.005
1719:History of neural networks
1131:project's importance scale
1031:Cognitive science articles
620:project's importance scale
531:project's importance scale
449:project's importance scale
352:project's importance scale
2980:C-Class Robotics articles
2784:Social Studies of Science
2615:Trans. IECE (in Japanese)
2410:10.1109/TSMC.1971.4308320
2316:Communications of the ACM
1885:was published in 1967 by
1347:Artificial neural network
1279:This page is archived by
1128:
1061:
997:
955:
904:
850:Category:Computer science
626:
613:
600:Computer science articles
562:
528:
477:
442:
383:
345:
294:
273:
80:Be welcoming to newcomers
2882:10.1109/TIT.1956.1056810
2855:10.1109/TIT.1954.1057468
2509:10.1109/TSSC.1969.300225
2105:Office of Naval Research
1908:(rectified linear unit)
1891:internal representations
1877:The first deep learning
852:and sub-categories with
492:WikiProject Neuroscience
2617:. J62-A (10): 658–665.
2459:10.1214/aoms/1177729586
1626:as a good example of a
3005:All Computing articles
2950:C-Class vital articles
2826:Joseph, R. D. (1960).
2404:. SMC-1 (4): 364–378.
2117:multilayer perceptrons
2095:In 1958, psychologist
2057:multilayer perceptrons
1682:pony in a strange land
1680:Do not reply anymore.
1632:pony in a strange land
1624:https://gwern.net/tank
1461:pony in a strange land
1309:on December 14, 2005.
1092:WikiProject Psychology
919:WikiProject Statistics
813:Computer science stubs
411:information technology
75:avoid personal attacks
2750:Werbos, P.J. (1975).
1879:multilayer perceptron
515:neuroscience articles
398:WikiProject Computing
259:on Knowledge (XXG)'s
252:level-5 vital article
199:Auto-archiving period
100:Neutral point of view
2931:. Spartan, New York.
2702:Psychological Review
2440:; Monro, S. (1951).
631:Things you can help
309:WikiProject Robotics
105:No original research
2287:10.1038/nature14539
2279:2015Natur.521..436L
2235:Schmidhuber, JĂĽrgen
1910:activation function
1115:psychology articles
942:Statistics articles
2664:10.1007/bf00344251
2623:10.1007/bf00344251
2027:User:Cosmia Nebula
1936:Kunihiko Fukushima
1902:Kunihiko Fukushima
1862:algorithm was the
1696:User:Cosmia Nebula
1646:User:Cosmia Nebula
1507:Kunihiko Fukushima
1483:JĂĽrgen Schmidhuber
1479:User:Cosmia Nebula
1386:User:Cosmia Nebula
1378:User:Cosmia Nebula
1368:As discussed with
429:Computing articles
261:content assessment
86:dispute resolution
47:
2925:Rosenblatt, Frank
2910:978-0-13-604259-4
2599:978-0-262-63022-1
2478:IEEE Transactions
2348:978-0-444-00020-0
2273:(7553): 436–444.
1868:Alexey Ivakhnenko
1650:Nils John Nilsson
1499:Alexey Ivakhnenko
1361:
1360:
1326:
1325:
1322:
1289:
1288:
1284:
1145:
1144:
1141:
1140:
1137:
1136:
1084:Psychology portal
1043:
1042:
1039:
1038:
1022:Cognitive science
985:Cognitive science
972:
971:
968:
967:
883:
882:
879:
878:
875:
874:
871:
870:
541:
540:
537:
536:
459:
458:
455:
454:
362:
361:
358:
357:
332:Robotics articles
230:
229:
66:Assume good faith
43:
3077:
2933:
2932:
2921:
2915:
2914:
2903:
2892:
2886:
2885:
2865:
2859:
2858:
2838:
2832:
2831:
2823:
2814:
2813:
2779:
2773:
2772:
2764:
2758:
2757:
2747:
2741:
2740:
2723:10.1037/h0042519
2716:
2697:
2691:
2688:
2682:
2681:
2647:
2641:
2640:
2610:
2604:
2603:
2584:
2578:
2577:
2575:
2563:
2557:
2556:
2539:
2519:
2513:
2512:
2492:
2486:
2485:
2474:Amari, Shun'ichi
2470:
2464:
2463:
2461:
2434:
2428:
2427:
2425:
2424:
2418:
2399:
2390:
2384:
2383:
2359:
2353:
2352:
2333:
2327:
2326:
2311:
2305:
2304:
2264:
2255:
2249:
2248:
2246:
2231:
2214:
2213:
2189:
2169:
2158:
2157:
2155:
2153:
2137:
2097:Frank Rosenblatt
2049:Frank Rosenblatt
1716:
1520:Seppo Linnainmaa
1349:. The result of
1338:
1337:
1331:
1316:
1305:Nature (journal)
1298:
1291:
1278:
1178:
1154:
1153:
1147:
1117:
1116:
1113:
1110:
1107:
1086:
1081:
1080:
1079:
1070:
1063:
1062:
1052:
1045:
1033:
1032:
1029:
1026:
1023:
1006:
999:
998:
993:
981:
974:
962:importance scale
944:
943:
940:
937:
934:
913:
906:
905:
900:
892:
885:
861:
855:
730:Computer science
659:Article requests
648:
641:
640:
628:
602:
601:
598:
595:
592:
591:Computer science
582:Computer science
571:
564:
563:
558:
554:Computer science
550:
543:
517:
516:
513:
510:
507:
486:
479:
478:
468:
461:
431:
430:
427:
424:
421:
392:
385:
384:
379:
371:
364:
334:
333:
330:
327:
324:
303:
296:
295:
290:
282:
275:
258:
249:
248:
241:
240:
232:
224:
210:
209:
200:
179:
178:
164:
95:Article policies
16:
3085:
3084:
3080:
3079:
3078:
3076:
3075:
3074:
2940:
2939:
2938:
2937:
2936:
2923:
2922:
2918:
2911:
2901:
2894:
2893:
2889:
2867:
2866:
2862:
2840:
2839:
2835:
2825:
2824:
2817:
2781:
2780:
2776:
2769:Report 85-460-1
2766:
2765:
2761:
2749:
2748:
2744:
2714:10.1.1.588.3775
2699:
2698:
2694:
2689:
2685:
2649:
2648:
2644:
2612:
2611:
2607:
2600:
2586:
2585:
2581:
2565:
2564:
2560:
2521:
2520:
2516:
2494:
2493:
2489:
2472:
2471:
2467:
2436:
2435:
2431:
2422:
2420:
2416:
2397:
2392:
2391:
2387:
2361:
2360:
2356:
2349:
2335:
2334:
2330:
2313:
2312:
2308:
2262:
2260:"Deep Learning"
2257:
2256:
2252:
2233:
2232:
2217:
2174:Neural Networks
2171:
2170:
2161:
2151:
2149:
2139:
2138:
2134:
2093:
1904:introduced the
1887:Shun'ichi Amari
1856:
1712:
1602:neuron doctrine
1525:Sepp Hochreiter
1511:Shun'ichi Amari
1503:Shun'ichi Amari
1487:Geoffrey Hinton
1366:
1335:
1285:
1179:
1173:
1151:
1114:
1111:
1108:
1105:
1104:
1082:
1077:
1075:
1030:
1027:
1024:
1021:
1020:
987:
941:
938:
935:
932:
931:
898:
867:
864:
859:
853:
841:Project-related
836:
817:
798:
772:
753:
734:
715:
696:
672:
599:
596:
593:
590:
589:
556:
514:
511:
508:
505:
504:
428:
425:
422:
419:
418:
377:
331:
328:
325:
322:
321:
288:
256:
246:
226:
225:
220:
197:
121:
116:
115:
114:
91:
61:
12:
11:
5:
3083:
3081:
3073:
3072:
3067:
3062:
3057:
3052:
3047:
3042:
3037:
3032:
3027:
3022:
3017:
3012:
3007:
3002:
2997:
2992:
2987:
2982:
2977:
2972:
2967:
2962:
2957:
2952:
2942:
2941:
2935:
2934:
2916:
2909:
2887:
2860:
2833:
2815:
2790:(3): 611–659.
2774:
2759:
2742:
2708:(6): 386–408.
2692:
2683:
2658:(4): 193–202.
2642:
2605:
2598:
2579:
2558:
2530:(2): 233–268.
2514:
2503:(4): 322–333.
2487:
2484:(16): 279–307.
2465:
2429:
2385:
2374:(2): 207–219.
2354:
2347:
2328:
2306:
2250:
2215:
2159:
2148:on 16 Dec 2023
2131:
2130:
2126:
2099:described the
2092:
2089:
2045:User:North8000
2041:
2040:
2039:
2038:
2037:
2036:
2035:
2034:
2033:
2032:
2031:
2030:
1965:User:North8000
1934:introduced by
1855:
1852:
1851:
1850:
1849:
1848:
1763:
1762:
1761:
1760:
1759:
1758:
1722:
1709:
1708:
1707:
1706:
1705:
1704:
1703:
1702:
1701:
1700:
1699:
1678:
1675:
1672:
1609:
1605:
1598:associationism
1592:
1588:
1581:
1574:
1566:
1565:
1564:
1561:
1557:
1550:
1543:
1472:
1471:
1455:
1451:
1446:
1439:
1435:
1431:
1424:
1382:User:North8000
1370:User:North8000
1365:
1362:
1359:
1358:
1351:the discussion
1339:
1328:
1324:
1323:
1315:
1310:
1299:
1287:
1286:
1277:
1276:
1273:
1272:
1271:
1270:
1265:
1260:
1255:
1250:
1245:
1240:
1235:
1230:
1225:
1220:
1215:
1213:2021/September
1210:
1205:
1200:
1195:
1190:
1182:
1181:
1180:
1175:
1171:
1169:
1168:
1155:
1143:
1142:
1139:
1138:
1135:
1134:
1127:
1121:
1120:
1118:
1101:the discussion
1088:
1087:
1071:
1059:
1058:
1053:
1041:
1040:
1037:
1036:
1034:
1007:
995:
994:
982:
970:
969:
966:
965:
958:Mid-importance
954:
948:
947:
945:
928:the discussion
914:
902:
901:
899:Mid‑importance
893:
881:
880:
877:
876:
873:
872:
869:
868:
866:
865:
863:
862:
845:
837:
835:
834:
828:
818:
816:
815:
809:
799:
797:
796:
791:
783:
773:
771:
770:
764:
754:
752:
751:
745:
735:
733:
732:
726:
716:
714:
713:
707:
697:
695:
694:
689:
683:
673:
671:
670:
664:
652:
650:
649:
637:
636:
624:
623:
616:Top-importance
612:
606:
605:
603:
586:the discussion
572:
560:
559:
557:Top‑importance
551:
539:
538:
535:
534:
527:
521:
520:
518:
501:the discussion
487:
475:
474:
469:
457:
456:
453:
452:
445:Top-importance
441:
435:
434:
432:
415:the discussion
393:
381:
380:
378:Top‑importance
372:
360:
359:
356:
355:
348:Top-importance
344:
338:
337:
335:
318:the discussion
304:
292:
291:
289:Top‑importance
283:
271:
270:
264:
242:
228:
227:
218:
216:
215:
212:
211:
181:
180:
118:
117:
113:
112:
107:
102:
93:
92:
90:
89:
82:
77:
68:
62:
60:
59:
48:
39:
38:
35:
34:
28:
13:
10:
9:
6:
4:
3:
2:
3082:
3071:
3068:
3066:
3063:
3061:
3058:
3056:
3053:
3051:
3048:
3046:
3043:
3041:
3038:
3036:
3033:
3031:
3028:
3026:
3023:
3021:
3018:
3016:
3013:
3011:
3008:
3006:
3003:
3001:
2998:
2996:
2993:
2991:
2988:
2986:
2983:
2981:
2978:
2976:
2973:
2971:
2968:
2966:
2963:
2961:
2958:
2956:
2953:
2951:
2948:
2947:
2945:
2930:
2926:
2920:
2917:
2912:
2907:
2900:
2899:
2891:
2888:
2883:
2879:
2875:
2871:
2864:
2861:
2856:
2852:
2848:
2844:
2837:
2834:
2829:
2822:
2820:
2816:
2811:
2808:
2804:
2801:
2797:
2793:
2789:
2785:
2778:
2775:
2770:
2763:
2760:
2755:
2754:
2746:
2743:
2738:
2735:
2731:
2728:
2724:
2720:
2715:
2711:
2707:
2703:
2696:
2693:
2687:
2684:
2679:
2676:
2672:
2669:
2665:
2661:
2657:
2653:
2646:
2643:
2638:
2635:
2631:
2628:
2624:
2620:
2616:
2609:
2606:
2601:
2596:
2593:. MIT Press.
2592:
2591:
2583:
2580:
2574:
2569:
2562:
2559:
2554:
2551:
2547:
2543:
2538:
2533:
2529:
2525:
2518:
2515:
2510:
2506:
2502:
2498:
2491:
2488:
2483:
2479:
2475:
2469:
2466:
2460:
2455:
2451:
2447:
2443:
2439:
2433:
2430:
2415:
2411:
2407:
2403:
2396:
2389:
2386:
2381:
2377:
2373:
2369:
2365:
2358:
2355:
2350:
2345:
2341:
2340:
2332:
2329:
2324:
2321:
2317:
2310:
2307:
2302:
2299:
2295:
2292:
2288:
2284:
2280:
2276:
2272:
2268:
2261:
2254:
2251:
2245:
2240:
2236:
2230:
2228:
2226:
2224:
2222:
2220:
2216:
2211:
2208:
2204:
2201:
2197:
2193:
2188:
2183:
2179:
2175:
2168:
2166:
2164:
2160:
2147:
2143:
2136:
2133:
2129:
2125:
2123:
2122:deep learning
2118:
2114:
2110:
2106:
2102:
2098:
2090:
2088:
2087:
2083:
2079:
2078:
2071:
2070:
2066:
2062:
2058:
2054:
2050:
2046:
2028:
2024:
2023:
2022:
2018:
2014:
2010:
2009:
2008:
2004:
2000:
1999:
1994:
1993:
1992:
1988:
1984:
1980:
1979:
1978:
1974:
1970:
1966:
1962:
1961:
1960:
1956:
1952:
1951:
1945:
1941:
1940:
1939:
1937:
1933:
1929:
1924:
1922:
1918:
1913:
1911:
1907:
1903:
1898:
1896:
1892:
1888:
1884:
1880:
1875:
1873:
1869:
1865:
1861:
1860:deep learning
1853:
1847:
1843:
1839:
1835:
1831:
1830:
1829:
1825:
1821:
1817:
1813:
1809:
1808:
1807:
1806:
1802:
1798:
1794:
1789:
1788:
1784:
1780:
1776:
1772:
1768:
1757:
1753:
1749:
1744:
1740:
1739:
1738:
1737:
1736:
1732:
1728:
1723:
1720:
1715:
1710:
1697:
1693:
1692:
1691:
1687:
1683:
1679:
1676:
1673:
1669:
1668:
1667:
1663:
1659:
1655:
1651:
1647:
1643:
1642:
1641:
1637:
1633:
1629:
1625:
1622:
1619:
1615:
1610:
1606:
1603:
1599:
1593:
1589:
1586:
1582:
1579:
1575:
1571:
1567:
1562:
1558:
1555:
1554:
1551:
1548:
1547:Pamphlet wars
1544:
1540:
1539:
1538:
1534:
1530:
1526:
1521:
1517:
1512:
1508:
1504:
1500:
1496:
1492:
1491:Yoshua Bengio
1488:
1484:
1480:
1476:
1475:
1474:
1473:
1470:
1466:
1462:
1456:
1452:
1447:
1444:
1440:
1436:
1432:
1429:
1425:
1423:
1419:
1418:
1417:
1416:
1412:
1408:
1407:
1400:
1399:
1395:
1391:
1387:
1383:
1379:
1375:
1371:
1363:
1356:
1352:
1348:
1344:
1340:
1333:
1332:
1329:
1320:
1313:
1308:
1307:
1306:
1300:
1297:
1293:
1292:
1282:
1275:
1274:
1269:
1266:
1264:
1261:
1259:
1258:2023/December
1256:
1254:
1253:2023/November
1251:
1249:
1246:
1244:
1241:
1239:
1236:
1234:
1233:2023/February
1231:
1229:
1228:2022/February
1226:
1224:
1221:
1219:
1216:
1214:
1211:
1209:
1206:
1204:
1203:2020/November
1201:
1199:
1196:
1194:
1191:
1189:
1186:
1185:
1184:
1183:
1166:
1165:
1160:
1159:
1149:
1148:
1132:
1126:
1123:
1122:
1119:
1102:
1098:
1094:
1093:
1085:
1074:
1072:
1069:
1065:
1064:
1060:
1057:
1054:
1051:
1047:
1035:
1018:
1017:
1012:
1008:
1005:
1001:
1000:
996:
991:
986:
983:
980:
976:
963:
959:
953:
950:
949:
946:
929:
925:
921:
920:
915:
912:
908:
907:
903:
897:
894:
891:
887:
858:
851:
847:
846:
844:
842:
838:
833:
830:
829:
827:
825:
824:
819:
814:
811:
810:
808:
806:
805:
800:
795:
792:
789:
785:
784:
782:
780:
779:
774:
769:
766:
765:
763:
761:
760:
755:
750:
747:
746:
744:
742:
741:
736:
731:
728:
727:
725:
723:
722:
717:
712:
709:
708:
706:
704:
703:
698:
693:
690:
688:
685:
684:
682:
680:
679:
674:
669:
666:
665:
663:
661:
660:
655:
654:
651:
647:
643:
642:
639:
638:
634:
630:
629:
625:
621:
617:
611:
608:
607:
604:
587:
583:
579:
578:
573:
570:
566:
565:
561:
555:
552:
549:
545:
532:
526:
523:
522:
519:
502:
498:
494:
493:
488:
485:
481:
480:
476:
473:
470:
467:
463:
450:
446:
440:
437:
436:
433:
416:
412:
408:
404:
400:
399:
394:
391:
387:
386:
382:
376:
373:
370:
366:
353:
349:
343:
340:
339:
336:
319:
315:
311:
310:
305:
302:
298:
297:
293:
287:
284:
281:
277:
272:
268:
262:
254:
253:
243:
239:
234:
233:
214:
213:
208:
204:
196:
192:
189:
187:
183:
182:
177:
173:
170:
167:
163:
159:
155:
152:
149:
146:
143:
140:
137:
134:
131:
127:
124:
123:Find sources:
120:
119:
111:
110:Verifiability
108:
106:
103:
101:
98:
97:
96:
87:
83:
81:
78:
76:
72:
69:
67:
64:
63:
57:
53:
52:Learn to edit
49:
46:
41:
40:
37:
36:
32:
26:
22:
18:
17:
2928:
2919:
2897:
2890:
2876:(3): 80–93.
2873:
2869:
2863:
2849:(4): 76–84.
2846:
2842:
2836:
2827:
2787:
2783:
2777:
2768:
2762:
2752:
2745:
2705:
2701:
2695:
2686:
2655:
2652:Biol. Cybern
2651:
2645:
2614:
2608:
2589:
2582:
2561:
2527:
2523:
2517:
2500:
2496:
2490:
2481:
2477:
2468:
2449:
2445:
2432:
2421:. Retrieved
2401:
2388:
2371:
2367:
2357:
2338:
2331:
2315:
2309:
2270:
2266:
2253:
2177:
2173:
2150:. Retrieved
2146:the original
2135:
2127:
2094:
2076:
2075:
2072:
2042:
1997:
1996:
1949:
1948:
1932:Neocognitron
1925:
1914:
1899:
1876:
1870:and Lapa in
1857:
1834:Michaelmalak
1820:Michaelmalak
1816:Neocognitron
1812:MOS:INSTRUCT
1793:WP:CONSENSUS
1790:
1775:WP:CONSENSUS
1764:
1743:WP:CONSENSUS
1654:WP:CONSENSUS
1628:microhistory
1617:
1569:
1405:
1404:
1401:
1367:
1354:
1327:
1311:
1303:
1302:
1263:2024/January
1248:2023/October
1223:2022/January
1218:2021/October
1198:2020/October
1162:
1156:
1090:
1014:
957:
917:
840:
839:
823:Unreferenced
821:
820:
802:
801:
776:
775:
757:
756:
738:
737:
719:
718:
700:
699:
676:
675:
657:
656:
615:
575:
506:Neuroscience
497:Neuroscience
490:
472:Neuroscience
444:
396:
347:
307:
267:WikiProjects
250:
202:
184:
171:
165:
157:
150:
144:
138:
132:
122:
94:
19:This is the
2438:Robbins, H.
1881:trained by
1721:subarticle.
1516:Alan Turing
1281:ClueBot III
1193:2020/August
148:free images
31:not a forum
2944:Categories
2573:1710.05941
2537:1505.03654
2452:(3): 400.
2423:2019-11-05
2368:Automatica
2244:2212.11279
2180:: 85–117.
2128:References
2101:perceptron
1771:Tryptofish
1748:Tryptofish
1578:presentism
1495:Yann LeCun
1268:2024/March
1238:2023/March
1106:Psychology
1097:Psychology
1056:Psychology
933:Statistics
924:statistics
896:Statistics
2710:CiteSeerX
2678:206775608
2637:206775608
2187:1404.7828
2113:Rochester
2077:North8000
2061:Speedboys
2013:Speedboys
1998:North8000
1983:Speedboys
1969:Speedboys
1950:North8000
1900:In 1969,
1838:Speedboys
1797:Speedboys
1779:Speedboys
1767:SamuelRiv
1727:SamuelRiv
1658:Speedboys
1614:Speedboys
1600:with the
1529:Speedboys
1422:Speedboys
1406:North8000
1390:Speedboys
1355:not moved
1319:this page
1312:Comments:
1243:2023/July
1208:2021/July
1188:2020/July
711:Computing
420:Computing
407:computing
403:computers
375:Computing
255:is rated
88:if needed
71:Be polite
21:talk page
2927:(1962).
2810:16786738
2737:12781225
2730:13602029
2553:12149203
2414:Archived
2294:26017442
2210:11715509
2203:25462637
1608:synapse)
1585:RNN page
1573:section?
1560:335-425.
1450:markets.
1158:Archives
1016:inactive
990:inactive
759:Maintain
702:Copyedit
323:Robotics
314:Robotics
286:Robotics
186:Archives
56:get help
29:This is
27:article.
2671:7370364
2630:7370364
2323:3074096
2301:3074096
2275:Bibcode
1872:Ukraine
1443:WP:NPOV
1420:Hello @
960:on the
740:Infobox
678:Cleanup
618:on the
447:on the
350:on the
257:C-class
203:90Â days
154:WPÂ refs
142:scholar
2803:285702
2267:Nature
2152:19 Dec
1944:WP:BRD
1921:Papert
1917:Minsky
1591:paper:
1493:, and
721:Expand
409:, and
263:scale.
126:Google
2902:(PDF)
2807:S2CID
2800:JSTOR
2734:S2CID
2675:S2CID
2634:S2CID
2568:arXiv
2550:S2CID
2532:arXiv
2417:(PDF)
2398:(PDF)
2320:S2CID
2298:S2CID
2263:(PDF)
2239:arXiv
2207:S2CID
2182:arXiv
2109:Clark
2043:Dear
1963:Dear
1832:Dear
1765:Dear
1694:Dear
1670:: -->
1644:Dear
1618:other
1594:: -->
1477:Dear
1457:: -->
1448:: -->
1343:moved
1164:Index
804:Stubs
778:Photo
635:with:
244:This
191:Index
169:JSTOR
130:books
84:Seek
2906:ISBN
2727:PMID
2668:PMID
2627:PMID
2595:ISBN
2344:ISBN
2291:PMID
2200:PMID
2154:2023
2082:talk
2065:talk
2017:talk
2003:talk
1987:talk
1973:talk
1955:talk
1919:and
1906:ReLU
1842:talk
1824:talk
1801:talk
1783:talk
1769:and
1752:talk
1731:talk
1711:The
1686:talk
1662:talk
1636:talk
1533:talk
1465:talk
1411:talk
1394:talk
1384:and
1353:was
162:FENS
136:news
73:and
2878:doi
2851:doi
2792:doi
2719:doi
2660:doi
2619:doi
2542:doi
2505:doi
2454:doi
2406:doi
2376:doi
2283:doi
2271:521
2192:doi
1570:are
1345:to
1125:???
952:Mid
610:Top
525:???
439:Top
342:Top
176:TWL
2946::
2872:.
2845:.
2818:^
2805:.
2798:.
2788:26
2786:.
2732:.
2725:.
2717:.
2706:65
2704:.
2673:.
2666:.
2656:36
2654:.
2632:.
2625:.
2548:.
2540:.
2528:43
2526:.
2499:.
2482:EC
2480:.
2450:22
2448:.
2444:.
2412:.
2400:.
2370:.
2366:.
2318:.
2296:.
2289:.
2281:.
2269:.
2265:.
2218:^
2205:.
2198:.
2190:.
2178:61
2176:.
2162:^
2124:.
2084:)
2067:)
2059:.
2019:)
2005:)
1989:)
1975:)
1957:)
1844:)
1826:)
1803:)
1785:)
1777:.
1754:)
1746:--
1733:)
1688:)
1664:)
1656:.
1638:)
1604:).
1535:)
1489:,
1485:,
1467:)
1413:)
1396:)
1167:)
860:}}
854:{{
405:,
201::
193:,
156:)
54:;
2913:.
2884:.
2880::
2874:2
2857:.
2853::
2847:4
2830:.
2812:.
2794::
2756:.
2739:.
2721::
2680:.
2662::
2639:.
2621::
2602:.
2576:.
2570::
2555:.
2544::
2534::
2511:.
2507::
2501:5
2462:.
2456::
2426:.
2408::
2382:.
2378::
2372:6
2351:.
2325:.
2303:.
2285::
2277::
2247:.
2241::
2212:.
2194::
2184::
2156:.
2080:(
2063:(
2015:(
2001:(
1985:(
1971:(
1953:(
1840:(
1822:(
1799:(
1781:(
1750:(
1729:(
1684:(
1660:(
1634:(
1531:(
1463:(
1409:(
1392:(
1357:.
1321:.
1283:.
1161:(
1133:.
1019:.
992:)
988:(
964:.
843::
826::
807::
790:)
781::
762::
743::
724::
705::
681::
662::
622:.
533:.
451:.
354:.
269::
195:1
188::
172:·
166:·
158:·
151:·
145:·
139:·
133:·
128:(
58:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.