Re: Representing knowlegde about pattern recognition
- From: N <n.m.keele@xxxxxxxxxxxxx>
- Date: Fri, 17 Aug 2007 09:14:42 -0700
On 15 Aug, 17:55, heiska mikko <mikk2...@xxxxxxxxxxx> wrote:
AI has to be able to learn and develop new ways of recognizing
patterns. AI must have modifiable templates for describing state
classes. It is not enough that computer code does different kinds of
recognizing tasks. AI must have those recognized pattern types
described with same kind of symbolic nodes and links as any other
knowledge / understanding-data. Then, computer code can be made from
that.
When learning to transcribe or understand voices of new language, AI
could test thousands of different recognition templates, guided by
some rough metrics indirectly indicating meaningfullness of text.
Yeh, I just bought a voice recognition programme, its taking ages
to train. I think the same problem would be found if we all talked
colloquial language, I think we'd be using classes of phrases and
have accents too.
Ok so we can recognise patterns like doing jigsaws say, smaller parts
appearing to make up a register collated into a pattern/net, or a
memory
but what about pattern manipulation? how is it that we can delve into
a theme, draw out part of a register and use the many components and
manipulate those patterns to generate something new? or just to
imagine
by recombination,
Cheers
n.
.
- References:
- Representing knowlegde about pattern recognition
- From: heiska mikko
- Representing knowlegde about pattern recognition
- Prev by Date: Re: Is technology part of evolution?
- Next by Date: Re: Is technology part of evolution?
- Previous by thread: Re: Representing knowlegde about pattern recognition
- Next by thread: YouTube's MOST iconoclastic films
- Index(es):
Relevant Pages
|
