[FoRK] Science without explicit theory
jbone at place.org
Sun Jul 6 18:59:42 PDT 2008
On Jul 6, 2008, at 8:27 PM, J. Andrew Rogers wrote:
> Having really, really large volumes of data allows you to recover
> algorithm bits inductively that would be unrecoverable at smaller
> volumes (underneath the information theoretic error floor),
Furthermore (my conjecture goes) the K-complexity of the recovered
algorithms rises with the size of the data set --- perhaps
logarithmically, James does that sound plausible or is the general
scaling rule more complex?
> No company anyone has heard of does this,
Well, if they do, you don't know that they do...
> The reason you will not see this coming out of Google any time soon
> is that their system is essentially based on parallel grep over
> points in 1-space. I do not think too many people would argue that
> this is the right tool for the job.
Depends on the job, I suppose. It the job is grepping 1-space, then
More information about the FoRK