From 05ceef7207d9b8618144f73ad0c6f560651d3e04 Mon Sep 17 00:00:00 2001 From: Joao Carreira Date: Sat, 15 Dec 2018 02:10:11 +0000 Subject: [PATCH] Fix cross-reference --- 043_DynamicErrorRobustness/DynamicErrorRobustness.tex | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/043_DynamicErrorRobustness/DynamicErrorRobustness.tex b/043_DynamicErrorRobustness/DynamicErrorRobustness.tex index d89f7c4..0369826 100644 --- a/043_DynamicErrorRobustness/DynamicErrorRobustness.tex +++ b/043_DynamicErrorRobustness/DynamicErrorRobustness.tex @@ -264,7 +264,7 @@ Finally, the output with the highest value is selected and the corresponding str In the proposed approach a shallow \ac{nn} using three layer, with 32 nodes in the hidden layer is used for simplicity and to avoid over-fitting, due to the limited test cases~\cite{NeuralNetworkDesign_2014}. By avoiding over-fitting, it is guaranteed that the proposed method would continue to work in future test conditions, not used for the network training. -The number of nodes in the hidden layer was determined by comparing the performance obtained for different number of neurons in this layer using the cross-entropy performance metric~\ref{CrossEntropy_2005}. +The number of nodes in the hidden layer was determined by comparing the performance obtained for different number of neurons in this layer using the cross-entropy performance metric~\cite{CrossEntropy_2005}. However, different network topologies with different number of neurons in each layer could also be used to predict between different error resilience techniques, as in the proposed method. \subsubsection{Training and validation}