Imputation means making up missing input data. Solomonoff induction implies
that the most likely values are those that minimize the Kolmogorov
complexity of the restored input, and it is not computable in general.

The theoretical motivation for Solomonoff induction is that all probability
distributions over an infinite set must favor short descriptions over
longer ones. Every description with p > 0 is more likely than an infinite
set of longer descriptions.

On Fri, Oct 25, 2019, 12:40 AM James Bowery <[email protected]> wrote:

> I don't see any theoretic grounding in the prior responses.  Isn't "AGI" a
> technical term?  Imputation of missing data is:
>
>  https://en.wikipedia.org/wiki/Imputation_(statistics)
> *Artificial General Intelligence List <https://agi.topicbox.com/latest>*
> / AGI / see discussions <https://agi.topicbox.com/groups/agi> +
> participants <https://agi.topicbox.com/groups/agi/members> + delivery
> options <https://agi.topicbox.com/groups/agi/subscription> Permalink
> <https://agi.topicbox.com/groups/agi/T36c83eb0aa31fc55-Mc11aa73f4c0a51d88e5af373>
>

------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T36c83eb0aa31fc55-M7c4b873a9080fac42de6987b
Delivery options: https://agi.topicbox.com/groups/agi/subscription

Reply via email to