From nobody Sun Apr 1 18:43:57 2018 Return-Path: X-Original-To: idnet@ietfa.amsl.com Delivered-To: idnet@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id C6609126CE8 for ; Sun, 1 Apr 2018 18:43:54 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -4.211 X-Spam-Level: X-Spam-Status: No, score=-4.211 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, T_RP_MATCHES_RCVD=-0.01] autolearn=ham autolearn_force=no Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id AtBMU5k3K9sT for ; Sun, 1 Apr 2018 18:43:52 -0700 (PDT) Received: from ns2.nict.go.jp (ns2.nict.go.jp [IPv6:2001:df0:232:300::2]) by ietfa.amsl.com (Postfix) with ESMTP id 86AF5126C89 for ; Sun, 1 Apr 2018 18:43:52 -0700 (PDT) Received: from gw2.nict.go.jp (gw2.nict.go.jp [133.243.18.251]) by ns2.nict.go.jp with ESMTP id w321hpjl016759; Mon, 2 Apr 2018 10:43:51 +0900 (JST) Received: from mail2.nict.go.jp (mail2.nict.go.jp [133.243.18.15]) by gw2.nict.go.jp with ESMTP id w321hpfo016753; Mon, 2 Apr 2018 10:43:51 +0900 (JST) Received: from spectre (unknown [133.243.28.118]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail2.nict.go.jp (NICT Mail Spool Server2) with ESMTPS id 13E0DD3CB; Mon, 2 Apr 2018 10:43:51 +0900 (JST) Date: Mon, 2 Apr 2018 10:43:50 +0900 From: Pedro Martinez-Julia To: Marie-Jose Montpetit Cc: idnet@ietf.org Message-ID: <20180402014349.GC10148@spectre> References: <8C38FF6D-E44C-436B-88CD-1C51D5306E3F@mjmontpetit.com> <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com> User-Agent: Mutt/1.9.4 (2018-02-28) X-Virus-Scanned: clamav-milter 0.99.3 at zenith2 X-Virus-Status: Clean Archived-At: Subject: Re: [Idnet] Seminar from Andrea Goldsmith (Stanford) on AI and Communication Systems X-BeenThere: idnet@ietf.org 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: Mon, 02 Apr 2018 01:43:55 -0000 Dear Marie-Jose, Thank you for sharing the report but, IMHO, without some backing slides or similar, such information just makes us anxious of more details about the solution :-D. Please, if possible, share the slides, a more detailed report, a video of the event, or something that we can use to study such solution. Thank you very much. Regards, Pedro On Wed, Mar 28, 2018 at 04:48:59PM -0400, Marie-Jose Montpetit wrote: > Andrea was in MIT yesterday and she presented a seminar entitiled: Can machine learning beat theory in communication system design?” > (fo those of you who do not know Andrea I suggest you Google her but in any case she is a highly reknowned wireless researcher from Stanford) > > She first explained why communications theory may not be enough to analyse next gen networks (she called them nG) because time-variance or lack of a real channel model (molecular communication which is like diffusion) and the need maybe to design new PHY especially for cellular for example questioning the frequency re-use model still used to define the cells and deal with interference. > > SHe went on to describe how her team use subject specific knowledge to define a new type of neural networks with sliding windows (a reference actually to coding where sliding window codes usually have the best performance). > > She applied the new ML to 2 cases: one estimation and the other for words recognition in the presence of noise (the famous source-destination joint coding problem) and 2 channels: a traditional Poisson channel and a molecular channel with base/acid representing 0s and 1s (another model BTW is the “vodka model where 1 shot is 1 and water is 0). The comparison on the Poisson channel was of course with the Viterbi Algorithm which is optimal when the channel is perfectly known. > > The results (to be published) show that of course when there is no uncertainty on the channel Viterbi is good. But the ML is consistently as much as good as optimal even as the uncertainty increases (like in a fast varying channel) and when under that uncertainty the Viterbi estimation degrades rapidly. > > With the pure molecular channel of course ML is the only solution and the results with the word recognition were excellent (next is imaging and video) because ML allows to dd semantics not just bit detection. Molecular channels BTW are considered for in-body communications. > > The conclusion was that with the nG communications ML may provide better results than traditional methods given that they are driven by subject experts not just a generic ML algorithm. Questions that remain include timing and repeating of the neural network training that of course would be system dependent. > > > mjm > > Marie-Jose Montpetit, Ph.D. > mariejo@mit.edu > marie@mjmontpetit.com > +1-781-526-2661 > @SocialTVMIT > > > > > _______________________________________________ > IDNET mailing list > IDNET@ietf.org > https://www.ietf.org/mailman/listinfo/idnet -- Pedro Martinez-Julia Network Science and Convergence Device Technology Laboratory Network System Research Institute National Institute of Information and Communications Technology (NICT) 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan Email: pedro@nict.go.jp --------------------------------------------------------- *** Entia non sunt multiplicanda praeter necessitatem *** From nobody Sun Apr 1 19:11:16 2018 Return-Path: X-Original-To: idnet@ietfa.amsl.com Delivered-To: idnet@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 3FA79126D74 for ; Sun, 1 Apr 2018 19:11:15 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -2.6 X-Spam-Level: X-Spam-Status: No, score=-2.6 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, DKIM_SIGNED=0.1, DKIM_VALID=-0.1, RCVD_IN_DNSWL_LOW=-0.7] autolearn=ham autolearn_force=no Authentication-Results: ietfa.amsl.com (amavisd-new); dkim=pass (2048-bit key) header.d=mjmontpetit-com.20150623.gappssmtp.com Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id CiKNvEuSOB9g for ; Sun, 1 Apr 2018 19:11:13 -0700 (PDT) Received: from mail-qk0-x22c.google.com (mail-qk0-x22c.google.com [IPv6:2607:f8b0:400d:c09::22c]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 8784B1243F3 for ; Sun, 1 Apr 2018 19:11:13 -0700 (PDT) Received: by mail-qk0-x22c.google.com with SMTP id v2so13839629qkh.10 for ; Sun, 01 Apr 2018 19:11:13 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=mjmontpetit-com.20150623.gappssmtp.com; s=20150623; h=mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=a/FyxUx7ZCIECTgyRvIiRr6WFZ3T2VLKqvXjlEeYg4g=; b=bOtPllis4mbcHG53RmMNFajjhSmArxkhzuA/YEFUtdx/sng9Q1JGAN42IVpuaoE9oi cPJ5zRII995QND0tdZkVDPLRXJu5qu97Y0U9SrnXQj2F2snLLZXv8AbI8Y9DHDpN3Vn0 m7fKDL4QIDV9yCIx8xPOiHAMPvZBF6vLYQP+DCdMFKvUhPKBKkJvt6AdLrYOf3x4Megs 2hD1FqEvkVwdmE52ez7uEyQ2WkPwJ+lao2t5zLf36UaZ6JeTlS3pMd6j0YGwRMmYgBUE i27IjX9qKnJFypQxHdEXLSlWIud2I54TtIuqshnb9kTdOb5SSqJcM8LQfk3W7P2t7g96 Mcqg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:subject:from:in-reply-to:date:cc :content-transfer-encoding:message-id:references:to; bh=a/FyxUx7ZCIECTgyRvIiRr6WFZ3T2VLKqvXjlEeYg4g=; b=f8KIR+MahEiNuXzyFRl9n6/xzNwMVFYZx+GqwFgSif26PnQmUAB2QVCRK2oRLAH78D sOirgwDV8oShDmuWPOU9230qKGWGND0bbXr98sTxGnzNgKGf4MjAW+cRAzh83hT5P7ky 4hVjvrihjnfBTNLRexnpts/Ynk6cds1NTVlnVlwSXm7Hd2rO9znFxZaM6pel5Nx4TY1E KhqUwZxo+RyX9o2f20kqXhV0nFJLdmbIoKWr5JNXqgnGwx5GWPIZKvF2knMqzrQTsiwA s7NKjIvZpWvFTpsqR62B0hoIJspIR2hFbzl2N9vjnRLjT+roayun6XBq+ayWgDiuDpJ8 6z2w== X-Gm-Message-State: ALQs6tC5OVDCqQ+Oes8/vSSAN7IUD2jrb/CRusEaGlD2MLeGgtVy0Wk+ bNnv1lP5JcSon1KWUE+SAMv2OA== X-Google-Smtp-Source: AIpwx48XimZ+uPiQoS+v0YHeJSNeBjRi4fDqlVV+8muaabRxMLcbVbEa70XtqwFt65lcb5oMsB3hFw== X-Received: by 10.55.173.13 with SMTP id f13mr10637665qkm.119.1522635072587; Sun, 01 Apr 2018 19:11:12 -0700 (PDT) Received: from winterfell.fios-router.home (pool-98-110-172-30.bstnma.fios.verizon.net. [98.110.172.30]) by smtp.gmail.com with ESMTPSA id r11sm10051745qkk.86.2018.04.01.19.11.11 (version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Sun, 01 Apr 2018 19:11:11 -0700 (PDT) Content-Type: text/plain; charset=utf-8 Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\)) From: Marie-Jose Montpetit In-Reply-To: <20180402014349.GC10148@spectre> Date: Sun, 1 Apr 2018 22:11:10 -0400 Cc: idnet@ietf.org Content-Transfer-Encoding: quoted-printable Message-Id: References: <8C38FF6D-E44C-436B-88CD-1C51D5306E3F@mjmontpetit.com> <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com> <20180402014349.GC10148@spectre> To: Pedro Martinez-Julia X-Mailer: Apple Mail (2.3124) Archived-At: Subject: Re: [Idnet] Seminar from Andrea Goldsmith (Stanford) on AI and Communication Systems X-BeenThere: idnet@ietf.org 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: Mon, 02 Apr 2018 02:11:15 -0000 I will try to find the information. There will be an article in JSAC = soon also. > On Apr 1, 2018, at 9:43 PM, Pedro Martinez-Julia = wrote: >=20 > Dear Marie-Jose, >=20 > Thank you for sharing the report but, IMHO, without some backing = slides > or similar, such information just makes us anxious of more details = about > the solution :-D. Please, if possible, share the slides, a more = detailed > report, a video of the event, or something that we can use to study = such > solution. Thank you very much. >=20 > Regards, > Pedro >=20 > On Wed, Mar 28, 2018 at 04:48:59PM -0400, Marie-Jose Montpetit wrote: >> Andrea was in MIT yesterday and she presented a seminar entitiled: = Can machine learning beat theory in communication system design?=E2=80=9D >> (fo those of you who do not know Andrea I suggest you Google her but = in any case she is a highly reknowned wireless researcher from Stanford) >>=20 >> She first explained why communications theory may not be enough to = analyse next gen networks (she called them nG) because time-variance or = lack of a real channel model (molecular communication which is like = diffusion) and the need maybe to design new PHY especially for cellular = for example questioning the frequency re-use model still used to define = the cells and deal with interference. >>=20 >> SHe went on to describe how her team use subject specific knowledge = to define a new type of neural networks with sliding windows (a = reference actually to coding where sliding window codes usually have the = best performance). >>=20 >> She applied the new ML to 2 cases: one estimation and the other for = words recognition in the presence of noise (the famous = source-destination joint coding problem) and 2 channels: a traditional = Poisson channel and a molecular channel with base/acid representing 0s = and 1s (another model BTW is the =E2=80=9Cvodka model where 1 shot is 1 = and water is 0). The comparison on the Poisson channel was of course = with the Viterbi Algorithm which is optimal when the channel is = perfectly known.=20 >>=20 >> The results (to be published) show that of course when there is no = uncertainty on the channel Viterbi is good. But the ML is consistently = as much as good as optimal even as the uncertainty increases (like in a = fast varying channel) and when under that uncertainty the Viterbi = estimation degrades rapidly. >>=20 >> With the pure molecular channel of course ML is the only solution and = the results with the word recognition were excellent (next is imaging = and video) because ML allows to dd semantics not just bit detection. = Molecular channels BTW are considered for in-body communications. >>=20 >> The conclusion was that with the nG communications ML may provide = better results than traditional methods given that they are driven by = subject experts not just a generic ML algorithm. Questions that remain = include timing and repeating of the neural network training that of = course would be system dependent. >>=20 >>=20 >> mjm >>=20 >> Marie-Jose Montpetit, Ph.D. >> mariejo@mit.edu >> marie@mjmontpetit.com >> +1-781-526-2661 >> @SocialTVMIT >>=20 >>=20 >>=20 >>=20 >> _______________________________________________ >> IDNET mailing list >> IDNET@ietf.org >> https://www.ietf.org/mailman/listinfo/idnet >=20 > --=20 > Pedro Martinez-Julia > Network Science and Convergence Device Technology Laboratory > Network System Research Institute > National Institute of Information and Communications Technology (NICT) > 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan > Email: pedro@nict.go.jp > --------------------------------------------------------- > *** Entia non sunt multiplicanda praeter necessitatem *** From nobody Sun Apr 1 19:15:48 2018 Return-Path: X-Original-To: idnet@ietfa.amsl.com Delivered-To: idnet@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 6AD22126D05 for ; Sun, 1 Apr 2018 19:15:46 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -4.211 X-Spam-Level: X-Spam-Status: No, score=-4.211 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, T_RP_MATCHES_RCVD=-0.01] autolearn=ham autolearn_force=no Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 7Zlx8HknqyYm for ; Sun, 1 Apr 2018 19:15:44 -0700 (PDT) Received: from ns1.nict.go.jp (ns1.nict.go.jp [IPv6:2001:df0:232:300::1]) by ietfa.amsl.com (Postfix) with ESMTP id DAA0A1243F3 for ; Sun, 1 Apr 2018 19:15:43 -0700 (PDT) Received: from gw1.nict.go.jp (gw1.nict.go.jp [133.243.18.250]) by ns1.nict.go.jp with ESMTP id w322FgrU020925; Mon, 2 Apr 2018 11:15:42 +0900 (JST) Received: from mail2.nict.go.jp (mail2.nict.go.jp [133.243.18.15]) by gw1.nict.go.jp with ESMTP id w322FgD6020865; Mon, 2 Apr 2018 11:15:42 +0900 (JST) Received: from spectre (unknown [133.243.28.118]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail2.nict.go.jp (NICT Mail Spool Server2) with ESMTPS id 8D9ABDAEC; Mon, 2 Apr 2018 11:15:42 +0900 (JST) Date: Mon, 2 Apr 2018 11:15:41 +0900 From: Pedro Martinez-Julia To: Marie-Jose Montpetit Cc: idnet@ietf.org Message-ID: <20180402021541.GD10148@spectre> References: <8C38FF6D-E44C-436B-88CD-1C51D5306E3F@mjmontpetit.com> <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com> <20180402014349.GC10148@spectre> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline Content-Transfer-Encoding: 8bit In-Reply-To: User-Agent: Mutt/1.9.4 (2018-02-28) X-Virus-Scanned: clamav-milter 0.99.3 at zenith1 X-Virus-Status: Clean Archived-At: Subject: Re: [Idnet] Seminar from Andrea Goldsmith (Stanford) on AI and Communication Systems X-BeenThere: idnet@ietf.org 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: Mon, 02 Apr 2018 02:15:46 -0000 On Sun, Apr 01, 2018 at 10:11:10PM -0400, Marie-Jose Montpetit wrote: > I will try to find the information. There will be an article in JSAC soon also. OK, thank you. Once the paper is published, please share it linked to this topic. Thank you very much. Regards, Pedro > > On Apr 1, 2018, at 9:43 PM, Pedro Martinez-Julia wrote: > > > > Dear Marie-Jose, > > > > Thank you for sharing the report but, IMHO, without some backing slides > > or similar, such information just makes us anxious of more details about > > the solution :-D. Please, if possible, share the slides, a more detailed > > report, a video of the event, or something that we can use to study such > > solution. Thank you very much. > > > > Regards, > > Pedro > > > > On Wed, Mar 28, 2018 at 04:48:59PM -0400, Marie-Jose Montpetit wrote: > >> Andrea was in MIT yesterday and she presented a seminar entitiled: Can machine learning beat theory in communication system design?” > >> (fo those of you who do not know Andrea I suggest you Google her but in any case she is a highly reknowned wireless researcher from Stanford) > >> > >> She first explained why communications theory may not be enough to analyse next gen networks (she called them nG) because time-variance or lack of a real channel model (molecular communication which is like diffusion) and the need maybe to design new PHY especially for cellular for example questioning the frequency re-use model still used to define the cells and deal with interference. > >> > >> SHe went on to describe how her team use subject specific knowledge to define a new type of neural networks with sliding windows (a reference actually to coding where sliding window codes usually have the best performance). > >> > >> She applied the new ML to 2 cases: one estimation and the other for words recognition in the presence of noise (the famous source-destination joint coding problem) and 2 channels: a traditional Poisson channel and a molecular channel with base/acid representing 0s and 1s (another model BTW is the “vodka model where 1 shot is 1 and water is 0). The comparison on the Poisson channel was of course with the Viterbi Algorithm which is optimal when the channel is perfectly known. > >> > >> The results (to be published) show that of course when there is no uncertainty on the channel Viterbi is good. But the ML is consistently as much as good as optimal even as the uncertainty increases (like in a fast varying channel) and when under that uncertainty the Viterbi estimation degrades rapidly. > >> > >> With the pure molecular channel of course ML is the only solution and the results with the word recognition were excellent (next is imaging and video) because ML allows to dd semantics not just bit detection. Molecular channels BTW are considered for in-body communications. > >> > >> The conclusion was that with the nG communications ML may provide better results than traditional methods given that they are driven by subject experts not just a generic ML algorithm. Questions that remain include timing and repeating of the neural network training that of course would be system dependent. > >> > >> > >> mjm > >> > >> Marie-Jose Montpetit, Ph.D. > >> mariejo@mit.edu > >> marie@mjmontpetit.com > >> +1-781-526-2661 > >> @SocialTVMIT > >> > >> > >> > >> > >> _______________________________________________ > >> IDNET mailing list > >> IDNET@ietf.org > >> https://www.ietf.org/mailman/listinfo/idnet > > > > -- > > Pedro Martinez-Julia > > Network Science and Convergence Device Technology Laboratory > > Network System Research Institute > > National Institute of Information and Communications Technology (NICT) > > 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan > > Email: pedro@nict.go.jp > > --------------------------------------------------------- > > *** Entia non sunt multiplicanda praeter necessitatem *** > -- Pedro Martinez-Julia Network Science and Convergence Device Technology Laboratory Network System Research Institute National Institute of Information and Communications Technology (NICT) 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan Email: pedro@nict.go.jp --------------------------------------------------------- *** Entia non sunt multiplicanda praeter necessitatem *** From nobody Thu Apr 5 05:52:07 2018 Return-Path: X-Original-To: idnet@ietfa.amsl.com Delivered-To: idnet@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 3934A12D87F for ; Thu, 5 Apr 2018 05:52:05 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -2.598 X-Spam-Level: X-Spam-Status: No, score=-2.598 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_LOW=-0.7, URIBL_BLOCKED=0.001] autolearn=ham autolearn_force=no Authentication-Results: ietfa.amsl.com (amavisd-new); dkim=pass (2048-bit key) header.d=mjmontpetit-com.20150623.gappssmtp.com Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 4b7Y_FuHWi3k for ; Thu, 5 Apr 2018 05:52:03 -0700 (PDT) Received: from mail-qk0-x22a.google.com (mail-qk0-x22a.google.com [IPv6:2607:f8b0:400d:c09::22a]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by ietfa.amsl.com (Postfix) with ESMTPS id 45ACD12778E for ; Thu, 5 Apr 2018 05:52:03 -0700 (PDT) Received: by mail-qk0-x22a.google.com with SMTP id p67so17618583qke.13 for ; Thu, 05 Apr 2018 05:52:03 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=mjmontpetit-com.20150623.gappssmtp.com; s=20150623; h=from:subject:message-id:date:to:mime-version; bh=2PcO9+nwdor4p0oq52osHP5HReHmBngcKPmRWRky/3c=; b=pqch5sCMLqCUZdkLI6E6nSeDBavF9l8KIwuhf21r9bBpLovO/noWBtP5/CADV6PFOy lx0aYnmK4V7OWIQA0zsJTPMQtM9541H87SaHtXiPWxT/MVIKFIUfEzA/VfMW+YxjZED1 vWYdVwB5HMNAd1IdkLp5LTTS5UVJiaVGHBYGOxlenpCvfQAbmcpRGQEjKVNATevchYDw mlzp7VZ5eTTWaMGL6vHe7EnVlGUIe5xpraMcUUxv81WTzupv2Glxwjdw9kT7SyGhzkWs yVDYTRDGhRslTBgUDji7X7ybjbS5/U5jQ2FI0yBQjkktk4ESt+IKC4gXbNdpX8/u46d4 O9Lg== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:from:subject:message-id:date:to:mime-version; bh=2PcO9+nwdor4p0oq52osHP5HReHmBngcKPmRWRky/3c=; b=dA0qeH6QoAG7KKfbOftmAzwWHvGIcUFcJOx8Dc5HuvkpcMHX9yVnkT+eihb1xjgVL6 LHiG6sO0NRFgUxCVggxv8vz1MFOxaODx234vO5SDU+NbmXl9ZB72UDpoNmTdx6T3KEb/ bLwraaf1u0XcyQQTnRY3BQezbiuRYm9dDsDR6XCQCw0OQ8QtRiPJIWBYhBKNQg3+pkuP 586uM2rpdcApXT9b+nOooPPYLuydf7XcrYRi5Cb7Hpd0zmaqDnfkcSpnsjoZgi1kuJoy 03IntlQxttRUbsPaM8qfWdFG2jIoRmc05uaXT1/FoKhENvyH9l9rsQc4tBloZANwAEeQ k1QA== X-Gm-Message-State: ALQs6tAVb75vGteaXs070Q/Tt1nDOaxcn4xusX09SptcYd1ozZPyeekl r63D4axE8+m522YHgpCiOefzgNlbzwU= X-Google-Smtp-Source: AIpwx49H2NlVLpkUOlZRb3FIlmujEqGHEXEDEuMupHsU591/836VkSPZ6Ym4FMeA3tibQCK9LGAouw== X-Received: by 10.55.31.17 with SMTP id f17mr28496545qkf.266.1522932722215; Thu, 05 Apr 2018 05:52:02 -0700 (PDT) Received: from winterfell.fios-router.home (pool-98-110-172-30.bstnma.fios.verizon.net. [98.110.172.30]) by smtp.gmail.com with ESMTPSA id b37sm6576670qtc.15.2018.04.05.05.52.01 for (version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Thu, 05 Apr 2018 05:52:01 -0700 (PDT) From: Marie-Jose Montpetit Content-Type: multipart/alternative; boundary="Apple-Mail=_2525DD0E-582E-4188-B4E5-E790C091D6D2" Message-Id: <5F75191A-478E-4287-854A-BA9BBBC0532A@mjmontpetit.com> Date: Thu, 5 Apr 2018 08:52:01 -0400 To: idnet@ietf.org Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\)) X-Mailer: Apple Mail (2.3124) Archived-At: Subject: [Idnet] Re-send: MIT Seminar Presentation X-BeenThere: idnet@ietf.org 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, 05 Apr 2018 12:52:05 -0000 --Apple-Mail=_2525DD0E-582E-4188-B4E5-E790C091D6D2 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset=us-ascii Thanks to Hesham ElBakoury: Attached is the presentation in the MIT seminar on ML for PHY design. The papers are generally posted to Nariman's publication website: = http://narimanfarsad.com/publications.html = mjm (it seems Hesham posted it to the list but some people did not receive = it - admins can you check?) Marie-Jose Montpetit, Ph.D. mariejo@mit.edu marie@mjmontpetit.com +1-781-526-2661 @SocialTVMIT --Apple-Mail=_2525DD0E-582E-4188-B4E5-E790C091D6D2 Content-Transfer-Encoding: 7bit Content-Type: text/html; charset=us-ascii Thanks to Hesham ElBakoury:

 Attached is the presentation in the MIT seminar on ML for PHY design.

The papers are generally posted to Nariman's publication website: http://narimanfarsad.com/publications.html


mjm

(it seems Hesham posted it to the list but some people did not receive it - admins can you check?)




Marie-Jose Montpetit, Ph.D.
mariejo@mit.edu
marie@mjmontpetit.com
+1-781-526-2661
@SocialTVMIT



--Apple-Mail=_2525DD0E-582E-4188-B4E5-E790C091D6D2-- From nobody Fri Apr 6 00:16:55 2018 Return-Path: X-Original-To: idnet@ietfa.amsl.com Delivered-To: idnet@ietfa.amsl.com Received: from localhost (localhost [127.0.0.1]) by ietfa.amsl.com (Postfix) with ESMTP id 271B912D86C for ; Wed, 4 Apr 2018 16:27:21 -0700 (PDT) X-Virus-Scanned: amavisd-new at amsl.com X-Spam-Flag: NO X-Spam-Score: -4.211 X-Spam-Level: X-Spam-Status: No, score=-4.211 tagged_above=-999 required=5 tests=[BAYES_00=-1.9, RCVD_IN_DNSWL_MED=-2.3, SPF_PASS=-0.001, T_RP_MATCHES_RCVD=-0.01] autolearn=ham autolearn_force=no Received: from mail.ietf.org ([4.31.198.44]) by localhost (ietfa.amsl.com [127.0.0.1]) (amavisd-new, port 10024) with ESMTP id 39FetJIuhWvp for ; Wed, 4 Apr 2018 16:27:19 -0700 (PDT) Received: from ns2.nict.go.jp (ns2.nict.go.jp [IPv6:2001:df0:232:300::2]) by ietfa.amsl.com (Postfix) with ESMTP id D2DA0126FB3 for ; Wed, 4 Apr 2018 16:27:18 -0700 (PDT) Received: from gw2.nict.go.jp (gw2.nict.go.jp [133.243.18.251]) by ns2.nict.go.jp with ESMTP id w34NRFHu073139; Thu, 5 Apr 2018 08:27:15 +0900 (JST) Received: from mail1.nict.go.jp (mail1.nict.go.jp [133.243.18.14]) by gw2.nict.go.jp with ESMTP id w34NRFY8073136; Thu, 5 Apr 2018 08:27:15 +0900 (JST) Received: from spectre (unknown [133.243.115.54]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail1.nict.go.jp (NICT Mail Spool Server1) with ESMTPS id F1C05100E5; Thu, 5 Apr 2018 08:27:14 +0900 (JST) Date: Thu, 5 Apr 2018 08:27:15 +0900 From: Pedro Martinez-Julia To: Hesham ElBakoury Cc: Marie-Jose Montpetit , "idnet@ietf.org" , Richard Li , "Kiran.Makhijani" , Padmadevi Pillay Esnault , Cedric Westphal , Dirk Kutscher , Ravi Ravindran , Yingzhen Qu , Lin Han , Alexander Clemm , Toerless Eckert Message-ID: <20180404232715.GP10148@spectre> References: <8C38FF6D-E44C-436B-88CD-1C51D5306E3F@mjmontpetit.com> <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com> <20180402014349.GC10148@spectre> <20180402021541.GD10148@spectre> MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Disposition: inline In-Reply-To: User-Agent: Mutt/1.9.4 (2018-02-28) X-Virus-Scanned: clamav-milter 0.99.3 at zenith2 X-Virus-Status: Clean Archived-At: X-Mailman-Approved-At: Fri, 06 Apr 2018 00:16:53 -0700 Subject: Re: [Idnet] Seminar from Andrea Goldsmith (Stanford) on AI and Communication Systems X-BeenThere: idnet@ietf.org 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: Wed, 04 Apr 2018 23:27:21 -0000 On Wed, Apr 04, 2018 at 06:33:08PM +0000, Hesham ElBakoury wrote: > Hi Pedro, Marie and all Dear Hesham, > I found this email thread while catching up on my emails ..... > > Attached you find Professor Andrea MIT presentation. The papers are > generally posted to Nariman's publication website: > http://narimanfarsad.com/publications.html Thank you very much for sharing the slides. I think they are very useful for our objective. > I started the discussion on using ML for communications with professor > John Cioffi (Stanford) in the 2nd half of last year. My idea is to > use ML for slot management in FlexE PHY to support hybrid multiplexing > in x-Ethernet. Both professor Andrea and Cioffi research in using ML > in the PHY is very interesting and I am hoping we can take advantage > of it in our Lab. Regarding your idea to use ML for slot management, I think such case can exploit broader AI methods beyond ML. It is one reason to evolve "MLRG" to "IDNET" and such case is quite interesting to explore from the wider perspective of general AI. If you like the idea, please let me know so I can find some common points to work with you. Thank you very much. > Hope this helps. > > Thanks > > Hesham Regards, Pedro -- Pedro Martinez-Julia Network Science and Convergence Device Technology Laboratory Network System Research Institute National Institute of Information and Communications Technology (NICT) 4-2-1, Nukui-Kitamachi, Koganei, Tokyo 184-8795, Japan Email: pedro@nict.go.jp --------------------------------------------------------- *** Entia non sunt multiplicanda praeter necessitatem ***