Title: Re: colt
Hi Juergen,
I don't know very well Solomonoff's work unfortunately.
But I know rather well the work by Putnam, Case and Smith,
Royer,
Blum etc. in limiting inference identification theories, which
are
part of colt too. (colt = computational learning theory =
t
Bill Jefferys wrote:
>
> At 7:09 PM +0200 8/2/02, Juergen Schmidhuber wrote:
>
> >beta decay is not random but due to some fast pseudo-random
> >generator which we should try to discover.
>
> This last claim would appear to contradict some well-supported
> predictions of quantum theory.
>
> Bi
or: simple explanations are better
explanations.
Most physicists, however, are not even aware of the fact that there
is a formal basis for their inductive science, provided by the field
of computational learning theory (COLT), in particular, the theory of
universal induction.
The contents of the
3 matches
Mail list logo