diff --git a/neural-networks/seminarpaper.tex b/neural-networks/seminarpaper.tex
index 44c08c2..fb3f9f9 100644
--- a/neural-networks/seminarpaper.tex
+++ b/neural-networks/seminarpaper.tex
@@ -561,7 +561,7 @@ the kind of a priori placement of neuromodulator sources won't work. The experim
 requires the robot to solve two tasks at the same time: It has
 to approach the lights and avoid obstacles. Since both tasks need to be solved
 at the same time and always it is not possible to devise two "seasons" or some
-similar seperation of learning time. Therefore the LMNN architecture is likely
+similar separation of learning time. Therefore the LMNN architecture is likely
 better suited.
 
 Nevertheless it would make sense to separate the learning for