11.4 Piaget’s Stages in the Context of Uncertain Inference 203
Epstein Suite indexes the text; the original document lives at its official source. We don't host the original file — view it on the official release to read it in full.
View the original on the official releaseDocument text
Text is machine OCR and may contain errors. Confirm against the original source above.
11.4 Piaget’s Stages in the Context of Uncertain Inference 203
Stage 4:Reflexive (Post-formal)
{ Inference Rules
New
Knowledge
4 }
| Knowledge about)
i World >
aaa
Inference Control Strategy |
Knowledge about how to
control inference
>
( Inference Rules )
a
i}
New
Knowledge
about how to
control
inference
:
Inference Control Strategy
4 ?) \
¢
\ “ { Inference Rules
\ ;
‘ c “ y’
\
\ | Knowledge about New knowledge about
‘ | inference rules [ > 7 inference rules
ee
Inference Control Strategy
wy
~~
~~
Fig. 11.8: The Reflexive Stage
stage adds an entire new feedback loop for reasoning about inference control itself, as shown in
Figure 11.8.
As a very concrete example, in later chapters we will see that, while PLN is founded on
probability theory, it also contains a variety of heuristic assumptions that inevitably introduce a
certain amount of error into its inferences. For example, PLN’s probabilistic deduction embodies
a heuristic independence assumption. Thus PLN contains an alternate deduction formula called
the “concept geometry formula’ that is better in some contexts, based on the assumption that
ConceptNodes embody concepts that are roughly spherically-shaped in attribute space. A highly
advanced CogPrime system could potentially augment the independence-based and concept-
geometry-based deduction formulas with additional formulas of its own derivation, optimized
to minimize error in various contexts. This is a simple and straightforward example of reflexive
cognition — it illustrates the power accessible to a cognitive system that has formalized and
reflected upon its own inference processes, and that possesses at least some capability to modify
these.
In general, AGI systems can be expected to have much broader and deeper capabilities for
self-modification than human beings. Ultimately it may make sense to view the AGI systems
we implement as merely “initial conditions" for ongoing self-modification and selforganization.
Chapter ?? discusses some of the potential technical details underlying this sort of thorough-
going AGI self-modification.
HOUSE_OVERSIGHT_013119
Have a question about what this document contains?
Ask the documents