From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mp12.migadu.com ([2001:41d0:306:2d92::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by ms9.migadu.com with LMTPS id ODPnKgVHy2S2NgAASxT56A (envelope-from ) for ; Thu, 03 Aug 2023 08:19:49 +0200 Received: from aspmx1.migadu.com ([2001:41d0:306:2d92::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by mp12.migadu.com with LMTPS id oHzRKgVHy2R4qgAAauVa8A (envelope-from ) for ; Thu, 03 Aug 2023 08:19:49 +0200 Received: from lists.gnu.org (lists.gnu.org [209.51.188.17]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by aspmx1.migadu.com (Postfix) with ESMTPS id D75ED36408 for ; Thu, 3 Aug 2023 08:19:48 +0200 (CEST) Authentication-Results: aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b="wzp/aqkY"; spf=pass (aspmx1.migadu.com: domain of "guix-devel-bounces+larch=yhetil.org@gnu.org" designates 209.51.188.17 as permitted sender) smtp.mailfrom="guix-devel-bounces+larch=yhetil.org@gnu.org"; dmarc=pass (policy=reject) header.from=laesvuori.fi ARC-Seal: i=1; s=key1; d=yhetil.org; t=1691043589; a=rsa-sha256; cv=none; b=oPBbv7/zbIVHyiPJKspafdJFokUggV5SgadV2jgNkTfHxxGMg62a7O4+SQm4Fq43w7FR3q 8l/m2WzquhkPVGbEl6U7TSphR0C06QOJvWYab99cuuKLKpsUHAl97DY7NsLwxLHcTj6C/Q 872e8rdm8ponn2MIB1AsDvHZLe5oRrMTPKxT7k9llobfnGHE8AJrpmT3bToCKGkhaZYXak o4iKv9wAH/3Om9ptiaPcTVYTrZDC9qCGckuKo4lPl8oDWAZ2oByeHThOC6m7/hdlNXPBzz WXkkzlnqGg7CSFe1s/GP3EHN+o5HjoDYqz0/FbcxGhMLJv6ogFcNeYVrO7fNpA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=yhetil.org; s=key1; t=1691043589; h=from:from:sender:sender:reply-to:subject:subject:date:date: message-id:message-id:to:to:cc:cc:mime-version:mime-version: content-type:content-type:in-reply-to:in-reply-to: references:references:list-id:list-help:list-unsubscribe: list-subscribe:list-post:dkim-signature; bh=U3+741CHxy+rtQGspOPKezroXLOwIjBISDHWQIdQbiY=; b=AEe/AieEI0nOwPxZDVuILW5C/+VmIe7PA8xWLXr3bKNfcLtvQOFSmVHHjNtJA0IiERBbjP b6ienpAguNJi9XtXbd/a3d15iQnEskTblcxbQkCZC2MzpZYgx21pIHLbhAzNc/FLGGm72c Vy4AWU11WpbITfF59/LaExOPdHZxklrycJHinwThqpYPZdbtdojFU+qkzzqIJSaWIiBG2l ebED0YO7E4rO7oObgyaVPLzdOkhcWh3i/Wp009bCeTVOOc1FFWyGNlviPEhfmrfhWFJq5m DPeXe9IukMXbWi9VEyjR87uJ2XdcFfCFvD77LmcD5K95hIud0/qEGEew4iPbrA== ARC-Authentication-Results: i=1; aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b="wzp/aqkY"; spf=pass (aspmx1.migadu.com: domain of "guix-devel-bounces+larch=yhetil.org@gnu.org" designates 209.51.188.17 as permitted sender) smtp.mailfrom="guix-devel-bounces+larch=yhetil.org@gnu.org"; dmarc=pass (policy=reject) header.from=laesvuori.fi Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qRRfo-0002mb-Su; Thu, 03 Aug 2023 02:19:00 -0400 Received: from eggs.gnu.org ([2001:470:142:3::10]) by lists.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qRRfn-0002mB-Jx for guix-devel@gnu.org; Thu, 03 Aug 2023 02:18:59 -0400 Received: from vmi571514.contaboserver.net ([75.119.130.101] helo=mail.laesvuori.fi) by eggs.gnu.org with esmtps (TLS1.2:ECDHE_RSA_AES_256_GCM_SHA384:256) (Exim 4.90_1) (envelope-from ) id 1qRRfl-0007KE-UJ for guix-devel@gnu.org; Thu, 03 Aug 2023 02:18:59 -0400 Received: from X-kone (83-100-46-149.rev.dnainternet.fi [83.100.46.149]) by mail.laesvuori.fi (Postfix) with ESMTPSA id A811934011B; Thu, 3 Aug 2023 08:18:59 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=laesvuori.fi; s=mail; t=1691043539; bh=U3+741CHxy+rtQGspOPKezroXLOwIjBISDHWQIdQbiY=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=wzp/aqkYWxEXRcjXPcBZhY3dfrnGryvnpVpdy42lyMlVOvUyJeHI4NHhDjsvUtjgH DAjQNXeeNIx+Y6/YhWU+/Us3bYB29tHSy45X/lfSj9/bwEorQrBlSU/vEAv6MWVxjt QP2RJ6Y/+fqBMnak+jff+lyVzP4Yy6jhLFUk4RsY= Date: Thu, 3 Aug 2023 09:18:50 +0300 From: Saku Laesvuori To: Nathan Dehnel Cc: guix-devel@gnu.org Subject: Re: Binary descriptors for OpenCV Message-ID: <20230803061850.lugers327lcxcrrq@X-kone> References: <20230801203700.67ef6l3ibg27wzpk@X-kone> <20230802044643.ibduhkxu3fvpoiok@X-kone> MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="ekhiznqpbirxqlgf" Content-Disposition: inline In-Reply-To: Received-SPF: pass client-ip=75.119.130.101; envelope-from=saku@laesvuori.fi; helo=mail.laesvuori.fi X-Spam_score_int: -20 X-Spam_score: -2.1 X-Spam_bar: -- X-Spam_report: (-2.1 / 5.0 requ) BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, DKIM_VALID_AU=-0.1, DKIM_VALID_EF=-0.1, SPF_HELO_PASS=-0.001, SPF_PASS=-0.001, T_SCC_BODY_TEXT_LINE=-0.01 autolearn=ham autolearn_force=no X-Spam_action: no action X-BeenThere: guix-devel@gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: "Development of GNU Guix and the GNU System distribution." List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: guix-devel-bounces+larch=yhetil.org@gnu.org Sender: guix-devel-bounces+larch=yhetil.org@gnu.org X-Migadu-Flow: FLOW_IN X-Migadu-Country: US X-Migadu-Spam-Score: -8.98 X-Migadu-Scanner: mx2.migadu.com X-Migadu-Queue-Id: D75ED36408 X-Spam-Score: -8.98 X-TUID: 55BePEkh66LR --ekhiznqpbirxqlgf Content-Type: text/plain; charset=us-ascii Content-Disposition: inline Content-Transfer-Encoding: quoted-printable > >You can always check what kind of data the program gives to the > >neural network as the program is free software. If the data is valid > >runtime input it is also valid training data. >=20 > That's not necessarily true. Like an image generating program will be > trained on image + caption pairs, but running it involves giving it > just the captions. Thus, running the model doesn't inherently show you > how to retrain the model. In that case aren't the captions the input to the model and the images the output? The training process tries to minimize the error between the correct output from the data set and the generated output. From using the model you do know what formats are expected as input and output, so you do have the information required for retraining. > >You can't exactly *know* that any extra training doesn't break the > >model but the same holds for editing the original training data. >=20 > You can know with more certainty that it doesn't break the model. Well, that depends on what kind of data editing and extra training we are comparing. If we remove a tiny bit from the original data set, it obviously is less likely to break the model than retraining it with bad data. But if you had a new training data set, it would not be any different to retrain the pretrained model on it instead of adding the new data set into the original training data and training from scratch. I should probably mention that I have never tried retraining models in practice and I'm basing all my arguments on my theoretical understading of how machine learning models work. --ekhiznqpbirxqlgf Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEoMkZR3NPB29fCOn/JX0oSiodOjIFAmTLRsoACgkQJX0oSiod OjLpFA/9EPDRzJQP8FZrffP3NLd3X7RQI4+W/5GmELsjXvXJMVUwGxHRKR37WxPH zFqUoYSZdOor2rhfElArrxGwEGL3/6uJykxOx8Jw0pg+qV+25vZQoGJoGi/2ciG0 Vci0wMcwrrv/CN3lC/j90/beuFM51TzTxTqvn0FZT1xzZsqjrRib1GbAeAjx1S4V /eiqu9oUSKRYBhbidEr8jCD8rLLyFCRKVrgvl+9Jf5Gjof1u4MTByEGqBL2Ngtjd yrbqXTzhq4jUAA9Dt5snRiLv9XgblQFvFDiPb046dAML/fh7spnsNx1EO7LI1jix JK+C49cZnEjsuvisnNdGZdUeK2rSxnBpiC0ks5EI4zO6JmVtE5ztxcdO++9FYhth 8qeWUWGkxyqFrbnQpNQZZezUuRKqmDdHyMe5Hh5RzN0CXwmhPkiidZUHuiXrVfS1 /Si+kiz3IbjHwkp0vzRUbpX8kRweX/LeYtdQqvHeKf+i7i2aNgMnp8jJoBs7KjYU phLEKLS64wuz7Oyt8/ltlNaSbBB/iTv/+u28JmWdHMVhcSQ0g2OUvL+/5lN+ZkhS BPd4G7BAWmLOlbD0/qc+ClJO7AVCebLPYk2D+St2JmYTQ33XOrbKPUsf+fq7SE5r mxMb/Ydy/G+U5IoTADFtMxhX0A1oNEmir77q6Wm3tE7Y0HNWfkk= =1MvQ -----END PGP SIGNATURE----- --ekhiznqpbirxqlgf--