On Thursday, June 30, 2022, at 10:15 AM, Rob Freeman wrote:
> But in the sense of having the same internal connectivity within two groups
> which are not directly connected together.
Yes, in the sense that inputs (input clusters) are parameterized with
derivatives ("connections") from lower-level cross-comp of their elements, etc.
Both input cluster and its param set can be hierarchical. The connection
between two or more compared inputs is the result of comparison of their
parameters, it's formed if their summed match is above local average.
On Thursday, June 30, 2022, at 10:15 AM, Rob Freeman wrote:
> If two separate clusters share a prediction, I don't see why you could not
> then connect them through such shared predictions which occur in a data set,
> without doing a direct comparison of their respective internal connectivity?
That shared prediction in your sense would be higher-level (output) cluster
that both of these clusters are in. Which only happens if they match, directly
or through some intermediate clusters that they match to. In the later case,
yes, there would be no direct comparison between the two on the lower level,
although they will likely be compared in a secondary confirmation mechanism on
a higher level.
On Thursday, June 30, 2022, at 10:15 AM, Rob Freeman wrote:
> Now, where my idea might come unstuck, is where there are two clusters which
> might be used to predict the same things on the basis of their internal
> similarity, as you suggest, but actually they have never been observed to
> share any predictions. In which case, yes, you would need to directly check
> any similarity in their clustering, and yours would be the only mechanism.
Do you mean two similar input-inputs that are not in the same input? In my
scheme there is conditional cross-comp among elements of matching clusters, if
the match is above corresponding order of local average. That's secondary to
comparison between param sets that mentioned above, would that solve your
problem? Again, both param sets and element sets of compared clusters are
nested, with max depth = elevation in system-wide search hierarchy.
------------------------------------------
Artificial General Intelligence List: AGI
Permalink:
https://agi.topicbox.com/groups/agi/T5d6fde768988cb74-M06b0b76455c53b520c9acff9
Delivery options: https://agi.topicbox.com/groups/agi/subscription
