From a51681103ae02a139b93428fd6e187ba30db6d25 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 20 Jun 2018 10:51:08 +0200 Subject: [PATCH] [NN] Improved wording and formatting Signed-off-by: Jim Martens --- neural-networks/seminarpaper.tex | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/neural-networks/seminarpaper.tex b/neural-networks/seminarpaper.tex index e87027e..1bcb7ed 100644 --- a/neural-networks/seminarpaper.tex +++ b/neural-networks/seminarpaper.tex @@ -488,7 +488,7 @@ forgetting. Hence their results will be used for the comparison in this section. Over multiple experiments of increasing difficulty the performance of modulated random search and modulated gaussian walk were tested. The difficulty ranged -from a positive light-tropism task in the first experiment(E1) over an +from a positive light-tropism task in the first experiment (E1) over an obstacle-avoidance task in the second experiment (E2), a combination of E1 and E2 in the third experiment (E3) to a more difficult variant of E3 in the fourth experiment (E4). The fifth experiment (E5) was a pendulum experiment. @@ -595,7 +595,7 @@ is better suited for combined tasks and localized learning than modulated gaussi walk. For single task environments or those where localized learning is not an option modulated gaussian walk is likely better suited than Hebbian learning. -Future work should look into the guesses that were taken here and analyze which +Future work should look into the assumptions that were taken here and analyze which network architecture is better and which learning rule is better for the kind of autonomous robot experiments that were conducted by Toutounji and Pasemann. In general the applicability of localized learning to bigger problems for example