2martens/uni
1
0
Fork 0
mirror of https://github.com/2martens/uni.git synced 2026-05-06 11:26:25 +02:00
Code Releases Activity

[NN] Improved wording and formatting

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2018-06-20 10:51:08 +02:00
parent 5b32039b09
commit a51681103a
1 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
neural-networks/seminarpaper.tex
View File

@ -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 Over multiple experiments of increasing difficulty the performance of modulated
random search and modulated gaussian walk were tested. The difficulty ranged 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 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 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. 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 walk. For single task environments or those where localized learning is not an
option modulated gaussian walk is likely better suited than Hebbian learning. 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 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 autonomous robot experiments that were conducted by Toutounji and Pasemann. In
general the applicability of localized learning to bigger problems for example general the applicability of localized learning to bigger problems for example