Thanks everyone for helping me "wring out" the whole dp/dt thing. Now for
the next part of "Steve's Theory..."
If we look at learning as extracting information from a noisy channel, in
which the S/N ratio is usually <<1, but where the S/N ratio is sometimes
very high, the WRONG thing to do is to e
Steve,
Well, I *still* think you are wasting your time with "flat"
(propositional) learning. I'm not saying there isn't still progress to
be made in this area, but I just don't see it as an area where
progress is critical. The main thing that we can do with propositional
models when we're dealing
Abram,
On 1/6/09, Abram Demski wrote:
>
> Well, I *still* think you are wasting your time with "flat"
> (propositional) learning.
I'm not at all sure that I understand what you are saying here, so some
elaboration is probably in order.
I'm not saying there isn't still progress to
> be made in
Steve,
Dp/dt methods do not fundamentally change the space of possible models
(if your initial mathematical claim of equivalence is true). What I am
saying is that that model space is *far* too small. Perhaps you know
some grammar theory? Markov models are not even as expressive as
regular grammar
Abram,
On 1/7/09, Abram Demski wrote:
>
> Steve,
>
> Dp/dt methods do not fundamentally change the space of possible models
> (if your initial mathematical claim of equivalence is true).
The claim is that a given neuron performs the same transformation, whether
on "object oriented" signals or d
Steve,
It seems that you misunderstood several of the things that I said.
Concerning grammar theory, I am only invoking the basics of the field,
so the wikipedia article should be enough if you want to know what I
meant by "regular grammar" and about them being only the "first level
of the hierarc