@FrameOfStack @bengoertzel Not outside of math, and no.
-
-
Replying to @FrameOfStack
@FrameOfStack If no truth then what? — More or less suitable (consistent, stable, sparse, relevant, efficient...) encoding.1 reply 0 retweets 1 like -
Replying to @FrameOfStack
@Plinz Taking the machine learning catch phrase "there are no correct models, only useful models" seriously1 reply 0 retweets 0 likes -
Replying to @FrameOfStack
@Plinz And what concept of "truth" this offers (essentially, "low generalization error") is bound up with the individual, not universal.2 replies 0 retweets 0 likes -
Replying to @FrameOfStack
@FrameOfStack Your teacher may still be more correct than you1 reply 0 retweets 0 likes -
Replying to @FrameOfStack
.
@FrameOfStack A teacher is a specialist for picking models to encode the world2 replies 1 retweet 4 likes -
Replying to @Plinz
@Plinz picking models is science, teaching is the art of creating minimal training sets that communicate them. cf http://pages.cs.wisc.edu/~jerryzhu/machineteaching/pub/MachineTeachingAAAI15.pdf …2 replies 0 retweets 1 like
@umruehren I am not sure if my best teacher taught by giving me training sets. They gave me questions.
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.