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

[Adeel Rehman <[e-mail]>]

Thank you David for your feedback :)

Sorry i forgot to include distro initially.

On Thu, Mar 23, 2017 at 1:40 PM, Adeel Rehman <[e-mail]>
wrote:

> Hi David
>
>
>
> You have point out excellent shortcomings of Machine learning applications
> in Networking field. I have been chasing the same question for a while now.
>
>
> I think part of the reason Network Packet data is very well
> structured/designed as compare to other data sources (image, text etc). The
> network data can be exploited using domain based algorithms very
> effectively. Applying ML algorithm to learn the rules of network traffic is
> somewhat costly compare to domain based algorithm. For e.g.
>
>
> a.       Learning shortest path, we have Dijkstra algorithm. Do we need
> ML for this?
>
>
> b.      TCP optimization. We have 3 or 4 Optimization algorithms that are
> very cost effective, run in client and server stack. Do we need ML for this?
>
>
> c.       There are ML papers that show HTTPS classification with good
> accuracy using SVM, and Decision tree algorithms. But do we need these
> algorithms? We can get classification using SSL SNI packet during SSL
> handshake and that would be 100% accurate.
>
> Having said that I think there are areas where Machine learning can be
> really helpful in detection non-structured behavior in Network Traffic
>
> a.       Anomaly Detection and Threat prevention. There are several
> algorithms out there but I think ML algorithms can outperform in this area.
> I know one security vendor effectively uses ML to prevent DDOS attacks.
>
> b.      Subscriber behavior, this is a hot topic for Telco operators. I
> think unsupervised topic modeling ML method can provide grouping of
> subscribers based on their usage. I actually have not seen any
> vendor/operator doing it currently, may be my knowledge is limited.
>
> c.       Self-orchestrated Network, this can be a big thing with NFV and
> Cloud applications. ML algorithms can play a vital part here. I see Cognet
> 5GPPP is taking initiative on this, but not much work from other vendors.
>
> and i apolo
>
> On Wed, Mar 22, 2017 at 1:29 PM, David Meyer <[e-mail]> wrote:
>
>> Folks,
>>
>> 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
>> http://www.1-4-5.net/~dmm/ml and http://www.1-4-5.net/~dmm/vita.html.
>> I'm looking forward to the discussion.
>>
>> Thanks,
>>
>> --dmm
>>
>>
>>
>>
>> [0]  http://packetpushers.net/podcast/podcasts/pq-show-107-a
>> pplicability-machine-learning-networking/
>>
>> [1]  http://sebastianruder.com/transfer-learning/index.html
>> [2]  http://datascience.ibm.com/blog/the-mathematics-of-machine-learning/
>> [3] https://openai.com/blog/
>> [4] http://distill.pub/
>> [5] http://rll.berkeley.edu/adversarial/arXiv2017_AdversarialAttacks.pdf
>> [6]  http://www.1-4-5.net/~dmm/ml/talks/2016/cor_ml4networking.pptx
>>
>>
>> _______________________________________________
>> IDNET mailing list
>> [e-mail]
>> https://www.ietf.org/mailman/listinfo/idnet
>>
>>
>
>
> --
> Syed  Rehman
>
>


-- 
Adeel Rehman
978-551-5511