[Ndn-interest] efficient lookup method
setori88 at gmail.com
Sun Jul 5 11:54:29 PDT 2015
On Mon, Jul 6, 2015 at 1:18 AM, Arunkumar Dhananjayan
<arunkd13 at gmail.com> wrote:
> I don't want to hijack this thread to discuss about SDRs, but can you
> enlighten me on how semantic similarity is ensured?
I would imagine shared language is the binding ensures semantic similarity.
> I think to have semantic similarity that everyone agree upon, we need a
> common encoding that will be used by everyone.
> I listened through the talk and it was really interesting. I find SDRs quite
> similar to Bloom Filters and there is considerable literature on using bloom
> filters to implement content based routing, where a common hash function is
> used, but the hashes themselves do not represent any semantic meaning. I am
> finding it intriguing that each bit in an SDR has a semantic meaning. It is
> probably true within a single brain, because of the coordinated learning it
> did, but I am pretty sure, the semantic meaning of the bits in the SDR are
> different in each of our brains.
> Probably to achieve a common semantic meaning for each bit, the entire
> network should act as a single brain and keep learning continuously. Or
> probably retrieving semantically close data is out of the scope of NDN and
> should probably be left to a totally different 'Google' layer.
NDN is the "google layer", it will break the google, facebook, dropbox
Though it looks like http://www.cortical.io/technology.html has put
down some very good foundations in this area.
How about reverse engineering their process and incorporating it into
the NDN mix?
Though there would need to be some kind of classifier which would map
SDR back to human readable words.
Maybe the Nupic classifer is enough to do this?
I don't know, there are many very interesting slants on this thought direction.
If there are people interested in creating an POC implementation of
this idea in Rust then lets collaborate.
More information about the Ndn-interest