2martens/uni
1
0
Fork 0
mirror of https://github.com/2martens/uni.git synced 2026-05-06 19:36:26 +02:00
Code Releases Activity

[NN] Finished outline

Browse Source 
Signed-off-by: Jim Martens <github@2martens.de>
This commit is contained in:
Jim Martens
2018-04-25 12:27:02 +02:00
parent 8600267879
commit 36723fffa9
2 changed files with 23 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
neural-networks/outline.tex
View File

@ -217,14 +217,18 @@ learning in an autonomous setup to analyse which of them if any can overcome
catastrophic forgetting. Attempts to overcome that were made by
Kirkpatrick\cite{Kirkpatrick2017}, Velez\cite{Velez2017} and Shmelkov\cite{Shmelkov2017}.
\section{Neuromodulation}
\label{sec:neuromodulation}
In the context of this paper plasticity refers to synaptic plasticity as described
in Citri\cite{Citri2008}. The process of learning itself, changing the weights,
is already considered plasticity. It is important however that the weights can
be changed during the lifetime of the neural network. Ordinary neural networks
trained with backpropagation are not involving plasticity.
Neuromodulation is a way to implement the second environmental feedback loop.
A Modulated Neural Network (MNN) contains neuromodulator cells (NMC), which are
attached to carrier neurons with a modulatory subnetwork (MSN).
\section{Catastrophic Forgetting}
\label{sec:catastrophicforgetting}
Neuromodulation can also be done based upon Diffusion.
Catastrophic Forgetting is a key issue for multi-task learning which itself
is a requirement for any neural network that is capable of solving more than
one type of problem.
\section{Plasticity}
\label{sec:plasticity}