2martens/uni
1
0
Fork 0
mirror of https://github.com/2martens/uni.git synced 2026-05-07 11:56:26 +02:00
Code Releases Activity

[NN] Improved conclusion

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2018-06-27 12:28:59 +02:00
parent c98f0e1bbf
commit f5523d540c
1 changed files with 17 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

28
neural-networks/seminarpaper.tex
View File

@ -516,6 +516,8 @@ solutions and averaged at \(12.5\) minutes per solution. This indicates that
gaussian walk mitigates catastrophic forgetting although it does not completely
remove it.
After the experiments related to modulated random search and modulated gaussian
walk the experiment related to localized learning is described.
The experiment setup for the localized learning approach was already mentioned.
After performing some tests Velez and Clune discovered that two functional
modules formed. One set of connections is learning during sommer and the other
@ -583,17 +585,21 @@ suited than Hebbian learning.
\section{Conclusion}
\label{sec:concl}
A second environmental feedback loop is important to tell autonomous systems
when to learn. But it is important how this feedback loop is working. Furthermore
it is important how the learning actually works. The comparison has shown that
localized learning utilizing neuromodulator sources can overcome catastrophic
forgetting for small networks in a very restricted setup. Furthermore the
comparison revealed that modulated random search is not part of a solution to
catastrophic forgetting. In a more general case it is likely that the LMNN
architecture is better than the sources architecture and that Hebbian learning
is better suited for combined tasks and localized learning than modulated gaussian
walk. For single task environments or those where localized learning is not an
option modulated gaussian walk is likely better suited than Hebbian learning.
The second environmental feedback loop is used to tell autonomous systems
when to learn. However the mere existence of such a loop is not enough. It matters
how this feedback loop is working and how it is connected with the rest of the
network. The weight change probability of both modulated random search and
modulated gaussian walk is the second environmental feedback loop but it was shown
that these two approaches are vastly different in their performance.
Therefore it is equally important how the learning actually works. The comparison
has shown that localized learning utilizing neuromodulator sources can overcome
catastrophic forgetting for small networks in a very restricted setup.
Furthermore the comparison revealed that modulated random search is not part of
a solution to catastrophic forgetting. In a more general case it is likely that
the LMNN architecture is better than the sources architecture and that Hebbian
learning is better suited for combined tasks and localized learning than modulated
gaussian 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 assumptions that were taken here and analyze which
network architecture is better and which learning rule is better for the kind of