Are these colleagues of yours? I notice you have a WUSTL address. You should invite them over into the NuPIC community! Maybe NuPIC can help with their efforts.
On 13/09/14 02:40, Archie, Kevin wrote: > There is still at least grant money going towards the idea that IPv4 > is not the end state of computer networking: > > https://news.wustl.edu/news/Pages/27333.aspx > > The PI on this grant is also founder/CTO of a startup > (http://observable.net) that uses machine learning/anomaly detection > for security and performance analytics. It's early but they have both > grant money coming in and real paying customers. (Last I talked to the > CTO they were hiring, but that was a few months ago.) > > - Kevin > > ------------------------------------------------------------------------ > *From:* nupic [[email protected]] on behalf of Alexander > Kettinen [[email protected]] > *Sent:* Friday, September 12, 2014 3:17 AM > *To:* Archie, Kevin > *Subject:* Re: machine intelligence & computer networking > > The problem requires no changes to the IPv4/6 protocols to work. What > is required is a hardware based subchannel utilization framework that > acts like a distributed and self-contained but expanding management > network. > > Similar to the ISL (Inter Switch Link) technology mentioned above. > http://www.cisco.com/c/en/us/support/docs/lan-switching/8021q/17056-741-4.html > > A "software defined network" as per VMWare or Cisco: > http://www.vmware.com/se/products/nsx/ > http://www.cisco.com/c/en/us/products/collateral/cloud-systems-management/extensible-network-controller-xnc/white-paper-c11-729757.html > > is not appropiate technology as these only replace hardware in a > virtualized local stack. > > .Alex > > 2014-09-12 5:33 GMT+02:00 Rik <[email protected] > <mailto:[email protected]>>: > > On 2014-09-12 00:01, Matthew Lohbihler wrote: > >> I think this would be a very interesting problem to work on. But >> it seems to me to implement what the article is talking about >> would require changes to the internet protocol, which of course >> would be a long and tortuous process. And without knowing what >> changes to IP will be approved, we can't know what data NuPIC >> would have available for analysis. > > N.B. in addition to what I said about private networks and > layering/tunneling as staging areas, there is an emergent trend > called "Software Defined Networking" (search for "OpenFlow", too) > that makes inroads into routers' traditional autonomy and allows > for some ventures into intelligent routing as far as I understand > the concept. > > Rik > > > > > > > > ------------------------------------------------------------------------ > > The material in this message is private and may contain Protected > Healthcare Information (PHI). If you are not the intended recipient, > be advised that any unauthorized use, disclosure, copying or the > taking of any action in reliance on the contents of this information > is strictly prohibited. If you have received this email in error, > please immediately notify the sender via telephone or return mail.
