<div dir="ltr">
<div>Dear Connectionists,</div><div><br></div><div>I posted a Medium article "<a href="https://medium.com/@rod_83597/learned-multidimensional-indexes-171c93fb581a" target="_blank">Learned Multidimensional Indexes</a>"
that I believe will be of interest to this community. It explains how
when items are represented as sets (i.e., entities which formally have
extension) as opposed to representing them as points (as is the case for
both localist representations and dense distributed representations,
i.e., vectors of reals), the items can simultaneously be physically
ordered on multiple uncorrelated underlying dimensions (latent
variables). This allows immediate best-match retrieval (approximate
nearest neighbors) on any of those uncorrelated, even completely
anti-correlated, dimensions. <br></div><div><br></div><div>The
essential insight is that the pattern of intersections over the sets
[e.g., sparse distributed representations (SDRs)] constitute "internal
indexes", i.e., internal to the codes themselves, which can be learned
directly from the data. Such internal indexes remove the need for the <i>external </i>indexes currently needed for conventional databases.</div><div><br></div><div>I look forward to thoughts / comments from the community.<br></div><div><br></div><div>Sincerely</div><div>Rod Rinkus</div>
<br clear="all"><br>-- <br><div dir="ltr" class="gmail_signature" data-smartmail="gmail_signature"><div dir="ltr"><div><div dir="ltr"><div><div dir="ltr"><div>Gerard (Rod) Rinkus, PhD<br>President and Chief Scientist<br>rod at neurithmicsystems dot com<br><a href="http://sparsey.com" target="_blank">Neurithmic Systems LLC</a><br>Newton, MA 02465<br>617-997-6272<br><br>Visiting Scientist<br>Volen Center for Complex Systems<br>Brandeis University, Waltham, MA<br>grinkus at brandeis dot edu<br><a href="http://people.brandeis.edu/%7Egrinkus/" target="_blank">http://people.brandeis.edu/~grinkus/</a><a href="http://people.brandeis.edu/%7Egrinkus/" target="_blank"></a>
</div></div></div></div></div></div></div></div>