From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mp10.migadu.com ([2001:41d0:403:4789::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by ms9.migadu.com with LMTPS id 2C5dCh1tyWTZvgAASxT56A (envelope-from ) for ; Tue, 01 Aug 2023 22:37:49 +0200 Received: from aspmx1.migadu.com ([2001:41d0:403:4789::]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits)) by mp10.migadu.com with LMTPS id wEGfCR1tyWTz9wAAG6o9tA (envelope-from ) for ; Tue, 01 Aug 2023 22:37:49 +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 A61D844A5E for ; Tue, 1 Aug 2023 22:37:48 +0200 (CEST) Authentication-Results: aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b=miIUOr+M; 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-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=yhetil.org; s=key1; t=1690922269; 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=+bLjwBEcEO2FHiDWAASWQeYssbYPm7+xpNagYGyriGc=; b=n4yxdhuOfT0jxfgvJs9DZLAeb+U1RgpI3SS/Toro8Fo8uwPgF6/o3o7deIHrjfCQUDGUqZ cLjkBikz1hIvOdxjnSckVD/pkQ6qnFwIZGMYp3CJFvsLJBH984/noYhy4WTIeNJC/7+yY5 4nBsoV9c/lxc3wQil69dYWxMLBicCqecjFVzRa03HAgSFKwL64WhuOaMiMLvUrfA8tlk+D ulg5hAvcRBgBTZt+gUO4VenIG9FP5l/CdtNpaxjALkoNkLtcifx3Qu4/tZfgIweRiTVpuP Uh8eF+af00k3X6ClBse8yFV28LtdLyyCTebHXZ9EG6O/HUwYLauur+hWXx6dgw== ARC-Authentication-Results: i=1; aspmx1.migadu.com; dkim=pass header.d=laesvuori.fi header.s=mail header.b=miIUOr+M; 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=1690922269; a=rsa-sha256; cv=none; b=YFvs037+rJ5xQK2V2ChGmgq37Whqyxt/jfxiYs32xFMOcDAKFgLZuI50z2MzoY5EhFBK+L 9biZ2e/sg3YVB4tQm1QbkkdcRTncuZCwV3ceS3MMCxJ7tyniYdErI3/3lr/MJXYei+ZL78 cDgvvB/RDDUVNfIup1ZoYVMpLK4mN/Ww3DbKhjNVfMqjcbSLahi6WLUZ4uhMHWxBww69l5 BJRYZ9ZtT4CHgUdbx2U/sV4+/RRVQHWx65rqdk0Sa6XqPqL0m6y8DsC+9iGmiTZ9+c0v02 GBFkcFmzFJQRY9IjzeTyT+hZthuKw1rLaTv3iWElH8DqG6/KzcE3zbOor5Fidg== Received: from localhost ([::1] helo=lists1p.gnu.org) by lists.gnu.org with esmtp (Exim 4.90_1) (envelope-from ) id 1qQw7D-0003uD-Vg; Tue, 01 Aug 2023 16:37:12 -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 1qQw7B-0003tp-LB for guix-devel@gnu.org; Tue, 01 Aug 2023 16:37:09 -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 1qQw77-0000CZ-48 for guix-devel@gnu.org; Tue, 01 Aug 2023 16:37:09 -0400 Received: from X-kone (unknown [192.130.254.9]) by mail.laesvuori.fi (Postfix) with ESMTPSA id 5164D340147; Tue, 1 Aug 2023 22:37:08 +0200 (CEST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=laesvuori.fi; s=mail; t=1690922228; bh=+bLjwBEcEO2FHiDWAASWQeYssbYPm7+xpNagYGyriGc=; h=Date:From:To:Cc:Subject:References:In-Reply-To; b=miIUOr+MC1ImxxICdMw9yHhLrjYa4Ozax08vACbWQaLVo89/zCvAjhvRbw7UPzDJx DWhQGSfDLOOb2WXITFCPqEdxkAE759efXYx2zyr+gIavJavIG4B2UYnTEdPyvN4uth AX4NLlg+uMOXe1x0DvLTOPD6Pc1oK+N7/18a/E00= Date: Tue, 1 Aug 2023 23:37:00 +0300 From: Saku Laesvuori To: Nathan Dehnel Cc: guix-devel@gnu.org Subject: Re: Binary descriptors for OpenCV Message-ID: <20230801203700.67ef6l3ibg27wzpk@X-kone> References: MIME-Version: 1.0 Content-Type: multipart/signed; micalg=pgp-sha256; protocol="application/pgp-signature"; boundary="kmxrvdwagr7754qv" 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: -8.17 X-Spam-Score: -8.17 X-Migadu-Queue-Id: A61D844A5E X-Migadu-Scanner: mx1.migadu.com X-TUID: eAY8PgMmg6BP --kmxrvdwagr7754qv Content-Type: text/plain; charset=us-ascii Content-Disposition: inline > Is this even practically possible? How do you re-train a blob you know > nothing about? To me this sounds similar to saying a compiled binary > is free software if the license allows you to decompile it and > deobfuscate it. If you know how to convert the blob to weights in the neural network (something the program has to do to make any use of the blob) and know the error function, you can continue the training with new data. This is not any different from training the model from scratch. In both cases we begin with some set of initial weights for a huge polynomial, take a sample of our training data, compute the polynomial for it and tweak the weights a bit if the result was not what we wanted. The only difference is that when training from scratch we begin with very bad guesses for all the weights. When we are tuning the blob we begin with much better guesses that are closer to the values we would actually want. The difference to a compiled binary program is that you would want to edit it in the source code form. You really would not want to edit the neural network by editing the original training data and retraining the entire network from scratch. The data set probably contains thousands, tens of thousands or even more random pictures that you would have to go through and see if they represent the data and results you want. It would be much easier to test whether the network gives the correct results and train it with new data that you know describes your problem better. --kmxrvdwagr7754qv Content-Type: application/pgp-signature; name="signature.asc" -----BEGIN PGP SIGNATURE----- iQIzBAABCAAdFiEEoMkZR3NPB29fCOn/JX0oSiodOjIFAmTJbOwACgkQJX0oSiod OjKYHBAAkiK5nPtHU/THB8vNOLPlqTfAiCKLtIwvqLiUSPDy32h48JQ7P556sV9W kXJBUw5ZHt54c5I7Q44ziSBIdPMB0CGsA5GxvB0ATZq5K3I1z/uTNBQdz0ILCqWx pqxzzfdVHX1wsYJwprRjQIuv0Nc2nnm/5sXse21XrkzGrsE/yeRyBRThvprryE5u 1KPIkzK+tYT8aadF0c2Gf4T/TOMKS9PCCIILiSItAQFn4jJzQiWtYOXUJdauWmAC LbaI8Vweg9GeJIB6ydQI3LCu+ZdAd+PI/FpoS8+2F+FfqoLP3cr6rav/IgBuwEsB TJGM+f7FXMdgB7bUtG7Aat3LXHdJzHuPxrP4dE97rnAEnAnUPESI7JREghlaUb4z AEXGeKJXthnm9kVlMlyj+BqxN0S/7skytC0d6RZPl9647Y7d5FIUIR+8l9AmR83a 46RissJJoRqA58YEkKgazox+XZQBxZILMvaqTF9Pkl81dD7CP3yLLfPiDGRcNabW tP8iN/vekpguBlzTfA3BRuAs8waJSsabU5vU/Dr4ttAund8y7nhA8Qn0Eo7QhkAI 77q5GyIQWqp+oQKxvuSsa3heajV1/3LhHpxBjkVGrB0Q4wj1BP/AQU/qqGTzQJlj kinWEPpDseeRUOE97bHcH+SfMu4ycOXgOR3az+BqF3Ex/HxngqQ= =Sw/q -----END PGP SIGNATURE----- --kmxrvdwagr7754qv--