<div dir="ltr"><div class="gmail_default" style=""><font face="times new roman, serif" style="" size="4">Tvi says: "Models which have true feedback (e.g. back to their own inputs) cannot learn by backpropagation"</font></div><div class="gmail_default" style=""><font face="times new roman, serif" size="4">Not sure where this is coming from, but it's certainly false. There's plenty of networks out there with feedback, and BPTT works with feedback connections. For a recent (2019) work that is trained on brain dynamics, see:</font></div><div class="gmail_default" style=""><h1 class="gmail-highwire-cite-title" id="gmail-page-title" style="box-sizing:border-box;margin:0px 0px 2rem;line-height:1.25;color:rgb(0,0,0);letter-spacing:-0.1rem"><a href="https://www.pnas.org/content/116/43/21854" style="font-weight:normal;letter-spacing:normal"><font face="times new roman, serif" style="" size="4">Recurrence is required to cap[ture the representational dynamics of the human visual system.</font></a><br></h1></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Sun, Oct 31, 2021 at 12:17 PM Tsvi Achler <<a href="mailto:achler@gmail.com">achler@gmail.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">Since the title of the thread is Scientific Integrity, I want to point out some issues about trends in academia and then especially focusing on the connectionist community.<div><br><div>In general analyzing impact factors etc the most important progress gets silenced until the mainstream picks it up <a href="https://www.nber.org/system/files/working_papers/w22180/w22180.pdf?fbclid=IwAR1zHhU4wmkrHASTaE-6zwIs6gI9-FxZcCED3BETxUJlMsbN_2hNbmJAmOA" rel="nofollow noopener" role="link" style="text-decoration-line:none;outline:none;list-style:none;border-width:0px;border-style:initial;border-color:initial;padding:0px;margin:0px;background-color:rgb(240,242,245);display:inline;box-sizing:border-box;font-family:"Segoe UI Historic","Segoe UI",Helvetica,Arial,sans-serif;font-size:15px" target="_blank">Impact Factiors in novel research www.nber.org/.../working_papers/w22180/w22180.pdf</a> and often this may take a generation <a href="https://www.nber.org/digest/mar16/does-science-advance-one-funeral-time?fbclid=IwAR1Lodsf1bzje-yQU9DvoZE2__S6R7UPEgY1_LxZCSLdoAYnj-uco0JuyVk" rel="nofollow noopener" role="link" style="text-decoration-line:none;outline:none;list-style:none;border-width:0px;border-style:initial;border-color:initial;padding:0px;margin:0px;background-color:rgb(240,242,245);display:inline;box-sizing:border-box;font-family:"Segoe UI Historic","Segoe UI",Helvetica,Arial,sans-serif;font-size:15px" target="_blank">https://www.nber.org/.../does-science-advance-one-funeral...</a> .</div><div><br></div><div>The connectionist field is stuck on feedforward networks and variants such as with inhibition of competitors (e.g. lateral inhibition), or other variants that are sometimes labeled as recurrent networks for learning time where the feedforward networks can be rewound in time.</div><div><br></div><div>This stasis is specifically occuring with the popularity of deep learning. This is often portrayed as neurally plausible connectionism but requires an implausible amount of rehearsal and is not connectionist if this rehearsal is not implemented with neurons (see video link for further clarification).</div><div><br></div><div>Models which have true feedback (e.g. back to their own inputs) cannot learn by backpropagation but there is plenty of evidence these types of connections exist in the brain and are used during recognition. Thus they get ignored: no talks in universities, no featuring in "premier" journals and no funding. </div><div><br></div><div>But they are important and may negate the need for rehearsal as needed in feedforward methods. Thus may be essential for moving connectionism forward.</div><div><br></div><div>If the community is truly dedicated to brain motivated algorithms, I recommend giving more time to networks other than feedforward networks.</div><div><br></div><div>Video: <a href="https://www.youtube.com/watch?v=m2qee6j5eew&list=PL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3&index=2" target="_blank">https://www.youtube.com/watch?v=m2qee6j5eew&list=PL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3&index=2</a></div><div><br></div><div>Sincerely,</div><div>Tsvi Achler</div><div><br></div><div><br></div></div></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Wed, Oct 27, 2021 at 2:24 AM Schmidhuber Juergen <<a href="mailto:juergen@idsia.ch" target="_blank">juergen@idsia.ch</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Hi, fellow artificial neural network enthusiasts!<br>
<br>
The connectionists mailing list is perhaps the oldest mailing list on ANNs, and many neural net pioneers are still subscribed to it. I am hoping that some of them - as well as their contemporaries - might be able to provide additional valuable insights into the history of the field.<br>
<br>
Following the great success of massive open online peer review (MOOR) for my 2015 survey of deep learning (now the most cited article ever published in the journal Neural Networks), I've decided to put forward another piece for MOOR. I want to thank the many experts who have already provided me with comments on it. Please send additional relevant references and suggestions for improvements for the following draft directly to me at <a href="mailto:juergen@idsia.ch" target="_blank">juergen@idsia.ch</a>:<br>
<br>
<a href="https://people.idsia.ch/~juergen/scientific-integrity-turing-award-deep-learning.html" rel="noreferrer" target="_blank">https://people.idsia.ch/~juergen/scientific-integrity-turing-award-deep-learning.html</a><br>
<br>
The above is a point-for-point critique of factual errors in ACM's justification of the ACM A. M. Turing Award for deep learning and a critique of the Turing Lecture published by ACM in July 2021. This work can also be seen as a short history of deep learning, at least as far as ACM's errors and the Turing Lecture are concerned.<br>
<br>
I know that some view this as a controversial topic. However, it is the very nature of science to resolve controversies through facts. Credit assignment is as core to scientific history as it is to machine learning. My aim is to ensure that the true history of our field is preserved for posterity.<br>
<br>
Thank you all in advance for your help! <br>
<br>
Jürgen Schmidhuber<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
<br>
</blockquote></div>
</blockquote></div><br clear="all"><div><br></div>-- <br><div dir="ltr" class="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div dir="ltr"><div>Gary Cottrell 858-534-6640 FAX: 858-534-7029<br></div><div>Computer Science and Engineering 0404<br>IF USING FEDEX INCLUDE THE FOLLOWING LINE: <br>CSE Building, Room 4130<br>University of California San Diego -<br>9500 Gilman Drive # 0404<br>La Jolla, Ca. 92093-0404<br><br></div><div>Email: <a href="mailto:gary@ucsd.edu" target="_blank">gary@ucsd.edu</a><br>Home page: <a href="http://www-cse.ucsd.edu/~gary/" target="_blank">http://www-cse.ucsd.edu/~gary/</a></div><div><span style="font-size:12.8px">Schedule: </span><span style="font-size:12.8px"><a href="http://tinyurl.com/b7gxpwo" style="font-size:12.8px" target="_blank">http://tinyurl.com/b7gxpwo</a></span><br></div><div><div style="font-size:12.8px"><br></div><div style="font-size:12.8px"><p style="font-family:"Book Antiqua";font-style:oblique;font-size:1.2em;color:rgb(0,0,0)">Listen carefully,<br style="font-style:oblique;font-size:1.2em">Neither the Vedas<br style="font-style:oblique;font-size:1.2em">Nor the Qur'an<br style="font-style:oblique;font-size:1.2em">Will teach you this:<br style="font-style:oblique;font-size:1.2em">Put the bit in its mouth,<br style="font-style:oblique;font-size:1.2em">The saddle on its back,<br style="font-style:oblique;font-size:1.2em">Your foot in the stirrup,<br style="font-style:oblique;font-size:1.2em">And ride your wild runaway mind<br style="font-style:oblique;font-size:1.2em">All the way to heaven.</p><p style="font-family:"Book Antiqua";font-style:oblique;font-size:1.2em;color:rgb(0,0,0)"><span style="font-size:1.2em;font-style:oblique">-- Kabir</span></p></div></div>
</div></div></div></div></div></div></div></div></div>