[Idnet] Seminar from Andrea Goldsmith (Stanford) on AI and Communication Systems

Marie-Jose Montpetit <marie@mjmontpetit.com> Wed, 28 March 2018 20:49 UTC

Return-Path: <marie@mjmontpetit.com>
X-Original-To: idnet@ietfa.amsl.com
Delivered-To: idnet@ietfa.amsl.com
Received: from localhost (localhost []) by ietfa.amsl.com (Postfix) with ESMTP id AA034127775 for <idnet@ietfa.amsl.com>; Wed, 28 Mar 2018 13:49:03 -0700 (PDT)
X-Virus-Scanned: amavisd-new at amsl.com
X-Spam-Flag: NO
X-Spam-Score: -2.6
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 ([]) by localhost (ietfa.amsl.com []) (amavisd-new, port 10024) with ESMTP id RKDwaIh-OYQo for <idnet@ietfa.amsl.com>; Wed, 28 Mar 2018 13:49:02 -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 21163127735 for <idnet@ietf.org>; Wed, 28 Mar 2018 13:49:02 -0700 (PDT)
Received: by mail-qk0-x22a.google.com with SMTP id s9so3869104qke.12 for <idnet@ietf.org>; Wed, 28 Mar 2018 13:49:02 -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:date:content-transfer-encoding:message-id :references:to; bh=39ezQyanXBFYCtKQIU+DHl1wvCaC8UW4epc3efZArxc=; b=1yIw5KsY1G8AVx0pybJ0rwhtw40X5EzKc2YrXEjEWdTjngTVvvM9w8he1md4dJl2dY ZvQbw7z+mar2KfGxj8BHfsXlV2w4vtRQX9weZmu3x/zdr+AdmZ97ZhS8VCFrYmTokEgs UEi7B2W2QMmnX+nLpukhXt2iJA6wtwDXVnZcCPHTs8xCcEClnDKRr0VFqwTonguGY4TF 1b3Y/DsGVDnw8SA/2gEJMuBiJ25SC1gZjvmRpEALJRZ9BHGpe+RvOIFkwcGpKU9wq4PV 68auraS2cZr+n6FJk+c94Brqpj6qTqTXoZB0yl38Fw6yOL0EZFIMOHDG59Z8oUSejlCY triQ==
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:date :content-transfer-encoding:message-id:references:to; bh=39ezQyanXBFYCtKQIU+DHl1wvCaC8UW4epc3efZArxc=; b=GzfSvW0MdbyK/jm8ik0622ttOmnILkDGKuwLu827VCrEbDzCW9Zm6lJKVz5fRiqK6o AASMSYw7tVkRgZ19BYUCUAHV9pQfj3P2OcipKF8pqiyl7Qkv8v5Arvy2oUQ4NXGPxjlC KPE6UXblksoRLmmTMNqt+DWza5jIAWNAHjwSGQtnrrTtwQk3nL1TpHnVZl4b7zcJnGdB tU4xfEtNEeKMhxcKJPsOeJIC0l41zuzN46zBqKsn5luY6+cqc+Re+YDxvLF7et4yCid0 nw6W1sO8qtdrivn381bsZrVlnPWvyMew0c8YQWc5YU3thpJunewE0yM8lpYFZlbw0Pwd Rwuw==
X-Gm-Message-State: ALQs6tALpu9K4FwPsJSZKcFZ+bv0JZnoDdpGFe3rsgUx38QUGNk9OS58 X+l/D7tNEi/pAVwRSxgigJc8rvbfeVE=
X-Google-Smtp-Source: AIpwx4+kbAQk1OdqouQ4noIvBMiuRv25QB6La8u/miLGlY3tEEguabuQUpgJ/dPFBx2T4bZzxGNKJA==
X-Received: by with SMTP id u15mr7429764qka.102.1522270141052; Wed, 28 Mar 2018 13:49:01 -0700 (PDT)
Received: from winterfell.fios-router.home (pool-98-110-172-30.bstnma.fios.verizon.net. []) by smtp.gmail.com with ESMTPSA id a4sm3306804qth.52.2018. (version=TLS1 cipher=ECDHE-RSA-AES128-SHA bits=128/128); Wed, 28 Mar 2018 13:49:00 -0700 (PDT)
Content-Type: text/plain; charset=utf-8
Mime-Version: 1.0 (Mac OS X Mail 9.3 \(3124\))
From: Marie-Jose Montpetit <marie@mjmontpetit.com>
Date: Wed, 28 Mar 2018 16:48:59 -0400
Content-Transfer-Encoding: quoted-printable
Message-Id: <3169CEEE-BAD1-475F-B216-A86D16C308E2@mjmontpetit.com>
References: <8C38FF6D-E44C-436B-88CD-1C51D5306E3F@mjmontpetit.com>
To: idnet@ietf.org
X-Mailer: Apple Mail (2.3124)
Archived-At: <https://mailarchive.ietf.org/arch/msg/idnet/SlTiRWHue47LC4RKvQ7WrPCU2gc>
Subject: [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 \(Intelligence-Defined Network\) " <idnet.ietf.org>
List-Unsubscribe: <https://www.ietf.org/mailman/options/idnet>, <mailto:idnet-request@ietf.org?subject=unsubscribe>
List-Archive: <https://mailarchive.ietf.org/arch/browse/idnet/>
List-Post: <mailto:idnet@ietf.org>
List-Help: <mailto:idnet-request@ietf.org?subject=help>
List-Subscribe: <https://www.ietf.org/mailman/listinfo/idnet>, <mailto:idnet-request@ietf.org?subject=subscribe>
X-List-Received-Date: Wed, 28 Mar 2018 20:49:03 -0000

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.


Marie-Jose Montpetit, Ph.D.