<div dir="ltr">Dear Gary,<div>Sorry, you are still not aware of, or did not read, my work:</div><div>No data sets are valid for conscious learning. Conscious learning must be learned on the fly. Please do not ask anybody to try any data sets any more since they are a dead end in AI.<br><br>If you are always spoon fed, you will never be able to understand how to get food yourself.</div><div><br><div>Please read my reasoning and proofs in my paper about the post-selection protocol flaw and the paper about conscious learning.</div><div><br></div><div><font color="#000000">J. Weng, "On Post Selections Using Test Sets
(PSUTS) in AI", in Proc. International Joint Conference on Neural
Networks, pp. 1-8, Shengzhen, China, July 18-22, 2021.
<a href="http://www.cse.msu.edu/%7eweng/research/PSUTS-IJCNN2021rvsd-cite.pdf" target="_blank">PDF file</a>.</font><br><br><font color="#000000">J. Weng, "3D-to-2D-to-3D Conscious Learning", in
Proc. IEEE 40th International Conference on Consumer Electronics, pp.
1-6, Las Vegas NV, USA, Jan.7-9, 2022.
<a href="http://www.cse.msu.edu/%7eweng/research/ConsciousLearning-ICCE-2022-rvsd-cite.pdf" target="_blank">PDF file</a>.</font><br><br>Best regards,</div><div>-John<br><br></div><div><div>Date: Thu, 10 Feb 2022 07:23:03 -0800<br>From: Gary Marcus <<a href="mailto:gary.marcus@nyu.edu" target="_blank">gary.marcus@nyu.edu</a>><br>To: Juyang Weng <<a href="mailto:juyang.weng@gmail.com" target="_blank">juyang.weng@gmail.com</a>><br>Cc: Post Connectionists <<a href="mailto:connectionists@mailman.srv.cs.cmu.edu" target="_blank">connectionists@mailman.srv.cs.cmu.edu</a>><br>Subject: Re: Connectionists: Stephen Hanson in conversation with Geoff<br> Hinton<br>Message-ID: <<a href="mailto:873A06DA-D7BC-4090-B2DE-49179685DBF8@nyu.edu" target="_blank">873A06DA-D7BC-4090-B2DE-49179685DBF8@nyu.edu</a>><br>Content-Type: text/plain; charset="utf-8"<br><br>Try your algorithm on datasets such as this <a href="https://ai.facebook.com/blog/introducing-unidentified-video-objects-a-new-benchmark-for-open-world-object-segmentation/" rel="noreferrer" target="_blank">https://ai.facebook.com/blog/introducing-unidentified-video-objects-a-new-benchmark-for-open-world-object-segmentation/</a><br><br>If you produce strong empirical results, the community will take notice.<br><br>> On Feb 9, 2022, at 10:54 PM, Juyang Weng <<a href="mailto:juyang.weng@gmail.com" target="_blank">juyang.weng@gmail.com</a>> wrote:<br>><br>> ?<br>> Dear Gary,<br>><br>> As my reply to Asim Roy indicated, the parts and whole problem that Geoff Hinton considered is ill-posed since it bypasses how a brain network segments the "whole" from 1000 parts in the cluttered scene. Only 10 parts belong to the whole.<br>><br>> The relation problem has also been solved and mathematically proven if one understands emergent universal Turing machines using a Developmental Network (DN). The solution to relation is a special case of the solution to the compositionality problem which is a special case of the emergent universal Turing machine.<br>><br>> I am not telling you "a son looks like his father because the father makes money to feed the son". The solution is supported by biology and a mathematical proof.<br>><br>> Best regards,<br>> -John<br>><br></div>-- <br><div dir="ltr" data-smartmail="gmail_signature"><div dir="ltr">Juyang (John) Weng<br></div></div></div></div></div>