Re: [Idnet] A few ideas/suggestions to get us going

Rana Pratap Sircar <> Thu, 23 March 2017 08:42 UTC

Return-Path: <>
Received: from localhost (localhost []) by (Postfix) with ESMTP id 0801E131481 for <>; Thu, 23 Mar 2017 01:42:44 -0700 (PDT)
X-Virus-Scanned: amavisd-new at
X-Spam-Flag: NO
X-Spam-Score: -4.219
X-Spam-Status: No, score=-4.219 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, HTML_MESSAGE=0.001, RCVD_IN_DNSWL_MED=-2.3, RCVD_IN_MSPIKE_H3=-0.01, RCVD_IN_MSPIKE_WL=-0.01, SPF_PASS=-0.001, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no
Authentication-Results: (amavisd-new); dkim=pass (1024-bit key)
Received: from ([]) by localhost ( []) (amavisd-new, port 10024) with ESMTP id q5zSdvF-LydC for <>; Thu, 23 Mar 2017 01:42:40 -0700 (PDT)
Received: from ( []) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by (Postfix) with ESMTPS id 22129131471 for <>; Thu, 23 Mar 2017 01:42:39 -0700 (PDT)
X-AuditID: c1b4fb25-ce3ff70000002d78-d4-58d38a7e18bb
Received: from (Unknown_Domain []) by (Symantec Mail Security) with SMTP id 98.AC.11640.E7A83D85; Thu, 23 Mar 2017 09:42:38 +0100 (CET)
Received: from ( by ( with Microsoft SMTP Server (TLS) id 14.3.319.2; Thu, 23 Mar 2017 09:42:37 +0100
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;; s=selector1-ericsson-com; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version; bh=VB/kqWaHyMgyCjrdEK52ToXxexrHmHv2BR/d1mrtwaQ=; b=jEiKZbKtdhGPXQT+qGWA2A+eDz15d9uFTr9iLbYj1onLMeOiNTJpnaTm18l0+HL9y0gfRR8bCpoNwhxxngzWU90PgWef+gV2VnPRr3hKzA5+SEiksJ/YKAl4fic5CGTfb0XtuXkA1M+w7Ml6hSzOfzVvhDStTvBk1ssIxOeD31s=
Received: from ( by ( with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_128_CBC_SHA256_P256) id 15.1.991.4; Thu, 23 Mar 2017 08:42:36 +0000
Received: from ([]) by ([]) with mapi id 15.01.0991.017; Thu, 23 Mar 2017 08:42:36 +0000
From: Rana Pratap Sircar <>
To: David Meyer <>, "" <>
Thread-Topic: [Idnet] A few ideas/suggestions to get us going
Thread-Index: AQHSozHu5+2wwRwqjU2j6iMywUBG/aGh7zZQ
Date: Thu, 23 Mar 2017 08:42:36 +0000
Message-ID: <>
References: <>
In-Reply-To: <>
Accept-Language: en-US
Content-Language: en-US
authentication-results:; dkim=none (message not signed) header.d=none;; dmarc=none action=none;
x-originating-ip: []
x-microsoft-exchange-diagnostics: 1; VI1PR0701MB1934; 7:qh/85lVCyWfHl6rhf+b6rqqYhnC0/0CbcsGOFLcpy6m5/AJQaBWoywfOkQu79QXwvR51m9BErzLsbfIMOrBy/SEMeOaulYqHJJMUz1icfQsxKbWdzFRK7PlYtyaZ/JsdRvgrcxvVgHVOjbkXF4RjmhFZeojUuAZuluC67bkctcxgiDa9V3sIRJIhNqNvZF2VKpqfVoI4x6QqDS06Pph5sj2OVQ5axU7Vs6XJse1KrthL+/qE78D7kwEXq3zqUUNmXvf0G8Vc5Oc+xs00VT0fLtG6/AFn7AhKf52cgTWh82iAaUtG4Z65xV0XbGwMYrxUqEmhM03WAJSdLtfCVpw8gA==
x-ms-office365-filtering-correlation-id: 125c3f71-23a0-40bb-cba4-08d471c88e94
x-microsoft-antispam: UriScan:; BCL:0; PCL:0; RULEID:(22001)(2017030254075); SRVR:VI1PR0701MB1934;
x-microsoft-antispam-prvs: <>
x-exchange-antispam-report-test: UriScan:(166708455590820)(21748063052155)(104084551191319);
x-exchange-antispam-report-cfa-test: BCL:0; PCL:0; RULEID:(6040375)(601004)(2401047)(5005006)(8121501046)(3002001)(10201501046)(6041248)(20161123562025)(20161123564025)(20161123560025)(20161123555025)(20161123558025)(6072148); SRVR:VI1PR0701MB1934; BCL:0; PCL:0; RULEID:; SRVR:VI1PR0701MB1934;
x-forefront-prvs: 0255DF69B9
x-forefront-antispam-report: SFV:NSPM; SFS:(10009020)(39450400003)(377454003)(6306002)(54896002)(19609705001)(74316002)(7696004)(102836003)(6116002)(3280700002)(966004)(790700001)(81166006)(5660300001)(7906003)(7736002)(122556002)(86362001)(25786009)(9686003)(99286003)(55016002)(236005)(53546009)(189998001)(5890100001)(2501003)(6436002)(606005)(8936002)(6506006)(77096006)(8676002)(9326002)(38730400002)(53936002)(53376002)(2950100002)(3660700001)(229853002)(2906002)(3846002)(33656002)(6246003)(54356999)(2900100001)(76176999)(66066001)(50986999); DIR:OUT; SFP:1101; SCL:1; SRVR:VI1PR0701MB1934;; FPR:; SPF:None; MLV:sfv; LANG:en;
spamdiagnosticoutput: 1:99
spamdiagnosticmetadata: NSPM
Content-Type: multipart/alternative; boundary="_000_VI1PR0701MB193499B59CC0B6C8EF2AFD5DAB3F0VI1PR0701MB1934_"
MIME-Version: 1.0
X-MS-Exchange-CrossTenant-originalarrivaltime: 23 Mar 2017 08:42:36.3444 (UTC)
X-MS-Exchange-CrossTenant-fromentityheader: Hosted
X-MS-Exchange-CrossTenant-id: 92e84ceb-fbfd-47ab-be52-080c6b87953f
X-MS-Exchange-Transport-CrossTenantHeadersStamped: VI1PR0701MB1934
X-Brightmail-Tracker: H4sIAAAAAAAAA+NgFlrJKsWRmVeSWpSXmKPExsUyM2K7vW5d1+UIg4crFS0OdW1kt2g/8oXZ gcljzd5jLB5LlvxkCmCK4rJJSc3JLEst0rdL4MpounmDuaCjlaniz/MXbA2Mc/4xdjFyckgI mEg8mr+KCcQWEljHKHGlnaWLkQvIPsEocWzhVDCHRaCXWWLx1iWMEJmZTBLtkz+zQjinGCUa l99gA+lnE7CSOHH8GSuILSLgJHHv0D8WEFtYwEbiUsseFoi4rcSb9VeZIWwjiRsbboPZLAKq Em9WN4LZvAIJEhe6m5ghbgqQuLGnA2w+p0CgxJT97WB3MwqISXw/tQbsbmYBcYlbT+YzQfwj ILFkz3lmCFtU4uXjf2CHMgr0MkqcuHmaHSKhKLH6wwRWCLuPWWL58joI21di8723QDUcQHac xN9fzhDhfIlf/c9YIOwYiQPrQW7mArLnMUn8mLSJCaJeRuLHMQOI+GxWiZX/VzNCPC8lcfdK J5QtI/Hizl5WiKPzJQ7PmcQygVF9FpIfZiFJzQKHhaDEyZlPgGwOoLimxPpd+hAlihJTuh+y Q9gaEq1z5rIjiy9gZF/FKFqcWpyUm25krJdalJlcXJyfp5eXWrKJEZiADm75rbqD8fIbx0OM AhyMSjy8BRMvRQixJpYVV+YeYpTgYFYS4fXtBgrxpiRWVqUW5ccXleakFh9ilOZgURLnddx3 IUJIID2xJDU7NbUgtQgmy8TBKdXAaLCc/+OOk/1+l8vmJ5zaWlzm0hnCtv65hexqwfjd+cGX n/aZFr/YGPPx6tHr3k/nPr652F66ufHw1ydehQ3dEZPb2mJDDi2aMsdX+Gr7vXOsfzgundmR f+BFivOBdR97f7kXJKoLB3FXc1hG/jrx5Ix8e0fYPZeDWx8vO3zV435wy5V6971s/5VYijMS DbWYi4oTAaOc/cE8AwAA
Archived-At: <>
Subject: Re: [Idnet] A few ideas/suggestions to get us going
X-Mailman-Version: 2.1.22
Precedence: list
List-Id: "The IDNet \(Intelligence-Defined Network\) " <>
List-Unsubscribe: <>, <>
List-Archive: <>
List-Post: <>
List-Help: <>
List-Subscribe: <>, <>
X-List-Received-Date: Thu, 23 Mar 2017 08:42:44 -0000

Hi Dave,

As always another wonderful initiative from you. I too have been struggling with the 3 points that you mentioned –

1.       Theory of Networking

2.       Open Datasets that are relevant to Networks and not the images and demography aspects – not too sure of the initiatives such as &

3.       Skills

I feel that apart from this, there are a couple of additional challenges –

1.       Networks have a fairly complex layered architecture. Thus, any problem statement needs to look at a smaller scope (assuming that behavior of network is sum of these scopes ~ which, in my humble opinion, is incorrect)

2.       Continuously and rapidly evolving technology

I would most definitely like to participate & contribute…

Best regards,
Ph: +91 88 00 22 4872
"You can't make the same mistake twice, the second time, it's not a mistake, it's a choice." - Anonymous

From: IDNET [] On Behalf Of David Meyer
Sent: Wednesday, March 22, 2017 10:59 PM
Subject: [Idnet] A few ideas/suggestions to get us going


I thought I'd try to get some discussion going by outlining some of my views as to why networking is lagging other areas in the development and application of Machine Learning (ML). In particular, networking is way behind what we might call the "perceptual tasks" (vision, NLP, robotics, etc) as well as other areas (medicine, finance, ...). The attached slide from one of my decks tries to summarize the situation, but I'll give a bit of an outline below.

So why is networking lagging many other fields when it comes to the application of machine learning? There are several reasons which I'll try to outline here (I was fortunate enough to discuss this with the packetpushers crew a few weeks ago, see [0]). These are in no particular order.

First, we don't have a "useful" theory of networking (UTON). One way to think about what such a theory would look like is by analogy to what we see with the success of convolutional neural networks (CNNs) not only for vision but now for many other tasks. In that case there is a theory of how vision works, built up from concepts like receptive fields, shared weights, simple and complex cells, etc. For example, the input layer of a CNN isn't fully connected; rather connections reflect the receptive field of the input layer, which is in a way that is "inspired" by biological vision (being very careful with "biological inspiration"). Same with the alternation of convolutional and pooling layers; these loosely model the alternation of simple and complex cells in the primary visual cortex (V1), the secondary visual cortex(V2) and the Brodmann area (V3). BTW, such a theory seems to be required for transfer learning [1], which we'll need if we don't want every network to be analyzed in an ad-hoc, one-off style (like we see today).

The second thing that we need to think about is publicly available standardized data sets. Examples here include MNIST, ImageNet, and many others. The result of having these data sets has been the steady ratcheting down of error rates on tasks such as object and scene recognition, NLP, and others to super-human levels. Suffice it to say we have nothing like these data sets for networking. Networking data sets today are largely proprietary, and because there is no UTON, there is no real way to compare results between them.

Third, there is a large skill set gap. Network engineers (us!) typically don't have the mathematical background required to build effective machine learning at scale. See [2] for an outline of some of the mathematical skills that are essential for effective ML. There is a lot more to this, involving how progress is made in ML (open data, open source, open models, in general open science and associated communities, see e.g., OpenAi [3], Distill [4], and many others). In any event we need build community and gain new skills if we want to be able to develop and apply state of the art machine learning algorithms to network data, at scale. The bottom line is that it will be difficult if not impossible to be effective in the ML space if we ourselves don't understand how it works and further, if we can build explainable systems (noting that explaining what the individual neurons in a deep neural network are doing is notoriously difficult; that said much progress is being made). So we want to build explainable, end-to-end trained systems, and to accomplish this we ourselves need to understand how these algorithms work, but in training and in inference.

This email is already TL;DR but I'll add one more here: We need to learn control, not just prediction. Since we live in an inherently adversarial environment we need to take advantage of Reinforcement Learning as well as the various attacks being formulated against ML; [5] gives one interesting example of attacks against policy networks using adversarial examples. See also slides 31 and 32 of [6] for some more on this topic.

I hope some of this gets us thinking about the problems we need to solve in order to be successful in the ML space. There's plenty more of this on and
I'm looking forward to the discussion.