I didn't mean that those abstract models need to be explicitly coded by AGI programmers, but than abstract model can be explained (or taught) to AGI and it then can use it to infer various relations among objects of the scene which are not explicitly given in textual description. This modeling of abstract model occurs by the same cognitive laws as any other reasoning within AGI. Derivation based on abstract models can be carried out by matching of learned templates of derivation steps allowed in given formalism by the same pattern-matching analogy-enabled mechanism.
On 10/12/07, a <[EMAIL PROTECTED]> wrote: > Vladimir Nesov wrote: > > > Generation of such abstract-description-based scenes can be a tedious > > process at start, involving calculations 'by hand' on part of AGI, but > > gradually through introduction of intermediate concepts this process > > will become more intuitive and finally world model will be as flexible > > as one directly obtained from vision. So, abstraction-based model can > > be used as surrogate vision supply, results of which can be more > > optimally reperceived. > > > I am against this approach because I think reasoning is only about > pattern matching. Separate pattern matchers have to be reprogrammed to > construct your models, so it is a waste of time. Abstract models are not > affective. > > ----- > This list is sponsored by AGIRI: http://www.agiri.org/email > To unsubscribe or change your options, please go to: > http://v2.listbox.com/member/?&; > -- Vladimir Nesov mailto:[EMAIL PROTECTED] ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=53014817-8fcec4
