From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from ffbox0-bg.mplayerhq.hu (ffbox0-bg.ffmpeg.org [79.124.17.100]) by master.gitmailbox.com (Postfix) with ESMTP id 2BC3947609 for ; Thu, 14 Sep 2023 18:25:39 +0000 (UTC) Received: from [127.0.1.1] (localhost [127.0.0.1]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTP id 138D268C6E2; Thu, 14 Sep 2023 21:25:36 +0300 (EEST) Received: from relay7-d.mail.gandi.net (relay7-d.mail.gandi.net [217.70.183.200]) by ffbox0-bg.mplayerhq.hu (Postfix) with ESMTPS id 21C48680A6D for ; Thu, 14 Sep 2023 21:25:30 +0300 (EEST) Received: by mail.gandi.net (Postfix) with ESMTPSA id 73EE320003 for ; Thu, 14 Sep 2023 18:25:29 +0000 (UTC) Date: Thu, 14 Sep 2023 20:25:28 +0200 From: Michael Niedermayer To: FFmpeg development discussions and patches Message-ID: <20230914182528.GP8640@pb2> References: <05e2d1c7-956b-4ce5-a1a2-69e83ae484ab@betaapp.fastmail.com> <20230908130949.GW8640@pb2> <70f536e22a2bd37306663e10c323a521ba88265d.camel@haerdin.se> <20230909135356.GA8640@pb2> <2bbc6979201dede22ce35048ac08b6542bb19cdf.camel@haerdin.se> MIME-Version: 1.0 In-Reply-To: <2bbc6979201dede22ce35048ac08b6542bb19cdf.camel@haerdin.se> X-GND-Sasl: michael@niedermayer.cc Subject: Re: [FFmpeg-devel] VDD conference invitation - Dublin 22-24 Sept 2023 X-BeenThere: ffmpeg-devel@ffmpeg.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: FFmpeg development discussions and patches List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Reply-To: FFmpeg development discussions and patches Content-Type: multipart/mixed; boundary="===============0192172590033235796==" Errors-To: ffmpeg-devel-bounces@ffmpeg.org Sender: "ffmpeg-devel" Archived-At: List-Archive: List-Post: --===============0192172590033235796== Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="lYtTbTuCUQxZgETo" Content-Disposition: inline --lYtTbTuCUQxZgETo Content-Type: text/plain; charset=iso-8859-1 Content-Disposition: inline Content-Transfer-Encoding: quoted-printable On Sat, Sep 09, 2023 at 09:23:35PM +0200, Tomas H=E4rdin wrote: > l=F6r 2023-09-09 klockan 15:53 +0200 skrev Michael Niedermayer: > > On Sat, Sep 09, 2023 at 09:04:25AM +0200, Tomas H=E4rdin wrote: > > > fre 2023-09-08 klockan 15:09 +0200 skrev Michael Niedermayer: > > [...] > >=20 > > > > AI based filters are neglegted at a time everything is shifting > > > > to neural networks and AI.=A0 > > >=20 > > > Good. AI is a meme. Polynomial regression is just as good. > >=20 > > Theres a lot i could reply but lets pick 2 choices > > 1. FFmpeg is about data compression so lets look at compression > > ill make it easy, just a "toy" project from fabrice, beat this with > > Polynomial regression > > https://bellard.org/ts_server/ts_zip.html >=20 > I have actually had something like this in mind. Also better predictors > for intra compression. >=20 > > 2. lets just ask AI, and while we can argue about this, i REALLY like > > to see > > your Polynomial regression producing anything that resembles english > > text > > heres chat gpts reply, first attempt: >=20 > I'm not sure what that wall of text is supposed to accomplish, a Markov > chain can produce similar output. It's just mystified statistics, or > machine laundered labour. Or AI voodoo as I've heard it referred to. > See the paper "Polynomial Regression as an Alternative to Neural Nets" > by Cheng et al Well, 20 years ago i had a similar oppinion, NN are just a inefficient way to approximate statistics. But i changed my mind when artificial neural networks started to outperform classical statistics. I see no voodoo and no mystified statistics. What i do see is that the stru= ctures and algorithms have advanced quite a bit while for some reason its still ca= lled a "neural network". But the name used is meaningless, isnt it? The paper you quote talks about neural networks as they where 25 years ago. The field has advanced rapidly in recent years. I dont know where it will go from here. maybe we move to algorithms that can no longer be called neural networks even with one trying hard. Or maybe it will continue with things resembling neural networks. To me this makes no difference. I just find the technology cool If you dont see the difference between modern networks and this paper, i su= ggest you look at teh paper "Attention Is All You Need" this is the foundation to systems like GPT. And while one surely can cast anything into a frame work of additions and m= ultiplcations or NAND gates. That doesnt capture the structure in a usefull way. thx [...] --=20 Michael GnuPG fingerprint: 9FF2128B147EF6730BADF133611EC787040B0FAB Homeopathy is like voting while filling the ballot out with transparent ink. Sometimes the outcome one wanted occurs. Rarely its worse than filling out a ballot properly. --lYtTbTuCUQxZgETo Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iF0EABEIAB0WIQSf8hKLFH72cwut8TNhHseHBAsPqwUCZQNQFAAKCRBhHseHBAsP qyqMAJ9ndiM2TjV/jFUkDn+chQWgvro4jQCfZ07G6083m6KUcFwH+ffejwqxwTc= =sF/L -----END PGP SIGNATURE----- --lYtTbTuCUQxZgETo-- --===============0192172590033235796== Content-Type: text/plain; charset="us-ascii" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Disposition: inline _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe". --===============0192172590033235796==--