Mail Archives: djgpp/1997/12/16/14:30:48
"A. Sinan Unur" <sinan DOT unur AT cornell DOT edu> writes:
>Paul Derbyshire wrote:
><SNIP>
>> you're in deep doodoo), or a certain editor-cum-operating-system I
>> shall not name, which has a learning curve like e^x and a manual the
>> size of a phone book and half as well organized ;-)
>that is supported by neither theorey nor fact. it is not supported by
>fact, because people do learn it. a learning curve such as e^x means
>there will never be any learning.
Actually it used to mean that in time x, an amount e^x is learned. But
this would give the phrase "steep learning curve" the opposite of its
common meaning. Therefore, it now seems to mean it takes time e^x to
learn an amount x.
> theoretically, for the concept of
>'learning curve' to have any meaning, the function should probably be
>strictly increasing and concave.
Actually, neither of these needs to be true: strictly increasing would
mean nothing can be forgotten, concave would mean one of two things: in
the first interpretation I gave above, it would mean that less is
learned in each successive unit of time. In the second interpretation
it would mean more is learned. Neither of these is commonly true.
There are usually periods of time where nearly nothing is learned,
separated by short periods where learning advances very rapidly.
--
Dan Luecking Dept. of Mathematical Sciences
luecking AT comp DOT uark DOT edu University of Arkansas
http://comp.uark.edu/~luecking/ Fayetteville, AR 72101
- Raw text -