Data do not understand cause and effect; functions do.https://twitter.com/DataSciFact/status/1012713607963009024 …
-
-
Replying to @Plinz
Do you think it’s meaningful to distinguish between the function that is instantiated in a given system and the system itself? That is, *the person* (as a brain/body instantiating a function) understands. This might be pedantic.
1 reply 0 retweets 0 likes -
Replying to @RealtimeAI
It is the other way around: while the brain implements the model function (and the modeling functions), the person that understands is instantiated by the functions.
2 replies 0 retweets 3 likes -
-
Am I wrong when I think brains ( their particular and unique functions) understand the world each by its own way, i.e. differently? Or do you mean some universal function - principle of understanding?
1 reply 0 retweets 1 like -
...i.e. the ability to understand symbols and abstracts?
1 reply 0 retweets 0 likes -
Replying to @RJsnda
To really understand means to map a domain on something you already know how to compute. Models are functions that explain how information relates to change in other information. The thing that thinks it understands is itself a model though.
2 replies 0 retweets 2 likes -
That last comment was good. More of that please, less vague Jedi tweets please
1 reply 0 retweets 1 like -
Replying to @bitpharma @RJsnda
One person's vague Jedi tweet another's boringly logical conclusion is. (Which ones do you find too vague? I realize that I often don't supply enough context.)
2 replies 0 retweets 2 likes -
Eg, the beginning of this thread was fueled by my annoyance about Pearl's implicit human innateness claim, supported by the wrong intuitive argument. Of course data are inert! but transitions are not, and causality is just a particular kind of transition model, not human magic.
2 replies 0 retweets 2 likes
Spelling this out in detail for someone who is still puzzled by the concept of causality and has not read any Pearl might require a full page, but then again, is it really so complicated that it demands all that verbosity?
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.