From 13245b802fedb3cdde0813973a88f099bfa8c0ba Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Thu, 24 May 2018 13:07:54 +0200 Subject: [PATCH] [NN] Improved reading flow Signed-off-by: Jim Martens --- neural-networks/seminarpaper.tex | 26 +++++++++++++++----------- 1 file changed, 15 insertions(+), 11 deletions(-) diff --git a/neural-networks/seminarpaper.tex b/neural-networks/seminarpaper.tex index e3bda8e..3e9f337 100644 --- a/neural-networks/seminarpaper.tex +++ b/neural-networks/seminarpaper.tex @@ -215,7 +215,7 @@ maxnames=2 Autonomous robots need to adapt to new situations. They have a need to learn for an entire life. In order to do this they need a second environmental feedback -loop that tells them when to learn.\cite{Toutounji2016} +loop that tells them when to learn\cite{Toutounji2016}. The learning itself is also described as plasticity. In the context of this paper the definition of synaptic plasticity given by Citri\cite{Citri2008} will be used. @@ -226,7 +226,9 @@ and backpropagation. When a network has to adapt to new situations, it has to learn new tasks. Usually the previously learned weights are largely forgotten. This phenomenon is called -catastrophic forgetting.\cite{French1999,McCloskey1989} +catastrophic forgetting\cite{French1999,McCloskey1989}. It is highly problematic, +because the weights encode the learning of a network. If they are forgotten or +rather overwritten the previously learned tasks cannot be fulfilled anymore. Since catastrophic forgetting is a key problem for autonomous learning, it is crucial to overcome it. In this paper I will present some approaches for @@ -236,8 +238,9 @@ catastrophic forgetting. \section{Catastrophic Forgetting} \label{sec:catastrophicforgetting} -This section presents the major research developments related to catastrophic -forgetting and explains what it actually is. It follows the review of French\cite{French1999}. +French\cite{French1999} did a review of the existing research about catastrophic +forgetting. The following paragraphs will follow this review and highlight the +major developments in research related to catastrophic forgetting. McCloskey and Cohen\cite{McCloskey1989} originally discovered the problem of catastrophic forgetting, which was referred to as catastrophic interference. This @@ -305,12 +308,13 @@ catastrophic forgetting at bay, has to be named. \section{Plasticity} \label{sec:plasticity} -Every neural network involves a learning aspect and hence plasticity, given our +Catastrophic forgetting requires learned weights that can be forgotten. +Every neural network learns and therefore deals with plasticity, given our definition of it. In this section three approaches for plasticity using diffusion-based neuromodulation are presented in more detail. Modulated Random Search and Modulated Gaussian Walk are using linearly modulated neural networks. They are taken from Toutounji and Pasemann\cite{Toutounji2016}. The third approach -was introduced by Velez and Clune\cite{Velez2017} uses diffusion-based neuromodulation +was introduced by Velez and Clune\cite{Velez2017} and uses diffusion-based neuromodulation for localized learning hence the name of the subsection here. \subsection{Modulated Random Search} @@ -413,7 +417,7 @@ to find different network topologies (structure and weights combined). \subsection{Modulated Gaussian Walk} \label{subsec:mgw} -Toutounji and Pasemann introduce the modulated gaussian walk. The key differences +The modulated gaussian walk is introduced by Toutounji and Pasemann. The key differences start with the parameters. There is no maximum sensitivity for the neuromodulator concentration. When a weight change occurs the new weight is not chosen randomly but rather the difference to be added to the current weight is sampled from a @@ -473,10 +477,10 @@ by the other season. This results in a localized learning. \section{Comparison regarding catastrophic forgetting} \label{sec:comparison} -In this section the three presented approaches for plasticity are compared with -regard to their ability to mitigate or overcome catastrophic forgetting. For both -the modulated random search and the modulated gaussian walk this aspect was -analyzed in the experiments conducted by Toutounji and Pasemann\cite{Toutounji2016}. +Given the presentations of the three approaches it is interesting to compare +them with regard to their ability to mitigate or overcome catastrophic forgetting. +For both the modulated random search and the modulated gaussian walk this aspect +was analyzed in the experiments conducted by Toutounji and Pasemann\cite{Toutounji2016}. Therefore the results of their work will be utilized for this comparison. Velez and Clune\cite{Velez2017} introduced the presented approach of localized learning to analyze its capability with respect to overcoming catastrophic