Re:A modern self-referential weight matrix that learns to mo...
by drewm1980 on Wednesday April 13, 2022 @03:20PM
(#31019003)
Start with the assumption that someone has already done it... Do a thorough literature survey... Ask experts working on the most similar thing. Don't be disheartened if you weren't the first; ideas don't have to be original to have value; some ideas need reviving from time to time, or were ahead of their time when first discovered.
Re:A modern self-referential weight matrix that learns to mo...
by Szpadel on Wednesday April 13, 2022 @07:59PM
(#31021835)
ML is still fairly new topic and if you have some idea there is high chance that nobody actually tried it yet
Re:A modern self-referential weight matrix that learns to mo...
by swagasaurus-rex on Wednesday April 13, 2022 @01:57PM
(#31017913)
Create a demo of it doing -something-. Literally anything. Then show it off and see where it goes.
Re:A modern self-referential weight matrix that learns to mo...
by hwers on Wednesday April 13, 2022 @03:42PM
(#31019294)
Write a paper about it. Post it on arxiv.org. Contact some open minded researchers on twitter or here (show HN) for critique.
Re:A modern self-referential weight matrix that learns to mo...
by nitrogen on Wednesday April 13, 2022 @07:26PM
(#31021570)
You have to be affiliated with an institution to submit to arxiv.
Re:A modern self-referential weight matrix that learns to mo...
by rsfern on Wednesday April 13, 2022 @09:54PM
(#31022586)
You don’t strictly need an institutional affiliation, but it makes things easier for sure. Arxiv has an endorsement process you can go through to post without an affiliation
Re:A modern self-referential weight matrix that learns to mo...
by jah242 on Wednesday April 13, 2022 @07:20PM
(#31021521)
Sounds like we are in very similar positions and have a very similar question :). My only real plan so far is to try and beat or match SOTA on a recent benchmark from a large corporate / research lab, give them an email and hope they are willing to talk to you.
Re:A modern self-referential weight matrix that learns to mo...
by daveguy on Wednesday April 13, 2022 @02:34PM
(#31018428)
Demo speaks louder than words. If you don't want to go into the details of how it works, it would still be interesting to just see where it over and under performs compared to existing systems.
Re:A modern self-referential weight matrix that learns to mo...
by mark_l_watson on Wednesday April 13, 2022 @04:38PM
(#31019932)
Absolutely! Also, if possible, a Colab (or plain Jupiter notebook) and data would be good.
Re:A modern self-referential weight matrix that learns to mo...
by nynx on Wednesday April 13, 2022 @02:00PM
(#31017955)
I’d make a blog and post about my experiments.
Re:A modern self-referential weight matrix that learns to mo...
by andai on Wednesday April 13, 2022 @02:02PM
(#31018003)
And a video too, please :)
Re:A modern self-referential weight matrix that learns to mo...
by javajosh on Wednesday April 13, 2022 @02:07PM
(#31018070)
Host it on a $5 VPS with full internet access and "see what happens".
Re:A modern self-referential weight matrix that learns to mo...
by ggerganov on Wednesday April 13, 2022 @02:25PM
(#31018330)
I would make a "Show HN" post
Re:A modern self-referential weight matrix that learns to mo...
by Eliezer on Wednesday April 13, 2022 @10:14PM
(#31022712)
Don't burn the capabilities commons. You probably don't have anything, in which case, why bother people? If you do have something, that advances AI capabilities and shortens the time before AGI; and while nobody actually has anything resembling a viable plan for surviving that, the fake plans tend to rely on having more time rather than less time.
Re:A modern self-referential weight matrix that learns to mo...
by voldacar on Wednesday April 13, 2022 @10:55PM
(#31022958)
A bit LARPy, don't you think?
Re:A modern self-referential weight matrix that learns to mo...
by ur-whale on Thursday April 14, 2022 @03:01AM
(#31024115)
> what would you do with it?
Use the "proof is in the pudding" method:
Do something with it - preferably useful - that no one else can.
Re:A modern self-referential weight matrix that learns to mo...
by Scene_Cast2 on Wednesday April 13, 2022 @02:38PM
(#31018473)
If you do end up posting any sort of musings on this topic, I'd be really interested in taking a look.
I am never sure if it is a waste of time or has some value.
If you guys had some unique ML technology that is different to what all the others do, what would you do with it?