Consequently, if we were to find some
other vector which is less than.
400 or 350 bits away from.
X then, the chance of that happening
purely at random is very small.
So if this vectors represent objects, it's
highly likely that these two vectors
represent the same object.
In many ways what we've done here is very
reminiscent, of locality sensitive
hashing.
However, associative memories.
Defer from.
Lsh or even indexing in that they don't
really store the objects.
So, what they do instead is they choose.
A set of random vectors.
A large number, M.
Could be a million, but certainly not
anywhere nearly as large as the space
itself.
And instances that are seen by this memory