I've done a new, clean, implementation of this (just the knn piece) at my
current company which has agreed to allow an open source contribution.
Thanks,
Randy
On Mon, Apr 25, 2011 at 11:09 PM, Ted Dunning wrote:
> Available cheaper at my old company.
>
>
> http://www.deepdyve.com/lp/association
Available cheaper at my old company.
http://www.deepdyve.com/lp/association-for-computing-machinery/symbolic-regression-using-nearest-neighbor-indexing-GmDA73L5II
On Mon, Apr 25, 2011 at 10:22 PM, Randall McRee wrote:
> Symbolic Regression using Nearest Neighbor
> Indexing
>
Charikar is the definitive reference for this method. See
[1] Charikar, M., Similarity estimation techniques from
rounding*.* In *Proceedings
of the Symposium on Theory of Computing*, 2002.
I also created a simple LSH NN method based on this idea (refined, I think)
which you can find here: Mc
Sounds like a variant of LSH to me.
See Wikipedia article on LSH with random projections.
On Sun, Apr 24, 2011 at 8:56 PM, Lance Norskog wrote:
> I just found this vector distance idea in a technical paper:
>
> Create a space defined by X random vectors. For you data vectors,
> take the cosine
This is the starting point of the way I've always seen people do
Locality Sensitive Hashing with floating point vectors. Once you
have these bit vectors, you can do minhash stuff on them to
complete LSH.
On Sun, Apr 24, 2011 at 8:56 PM, Lance Norskog wrote:
> I just found this vector distance i
I just found this vector distance idea in a technical paper:
Create a space defined by X random vectors. For you data vectors,
take the cosine distance to each random vector and save the sign of
the value as a bit. This gives a bit set of X bits.
There could be another distance and algorithm for
