Fixed typo

Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens 2019-03-10 11:49:46 +01:00
parent 89fa915e33
commit 74d0a2e38f
1 changed files with 2 additions and 2 deletions

View File

@ -12,9 +12,9 @@ the design of so called algorithms, a term often used in public
discourse for applied neural networks, is the question of discourse for applied neural networks, is the question of
algorithmic accountability\cite{Diakopoulos2014}. algorithmic accountability\cite{Diakopoulos2014}.
The charme of supervised neural networks, that they can learn from The charm of supervised neural networks, that they can learn from
input-output relations and figure out by themselves what connections input-output relations and figure out by themselves what connections
are necessary for that, is also their achilles heel. This feature are necessary for that, is also their Achilles heel. This feature
makes them effectively black boxes. It is possible to question the makes them effectively black boxes. It is possible to question the
training environment, like potential biases inside the data sets, or training environment, like potential biases inside the data sets, or
the engineers constructing the networks but it is not really possible the engineers constructing the networks but it is not really possible