From ef4e9974d1f6047d574c0c27e3df108c82e9763d Mon Sep 17 00:00:00 2001 From: Michel Salomon Date: Mon, 10 Oct 2011 16:40:41 +0200 Subject: [PATCH] C'est de la merde ce git --- main.tex | 20 -------------------- 1 file changed, 20 deletions(-) diff --git a/main.tex b/main.tex index 79209de..49564db 100644 --- a/main.tex +++ b/main.tex @@ -556,11 +556,7 @@ condition $\left(S,(x_1^0,\dots, x_n^0)\right) \in \llbracket 1;n \rrbracket^{\mathds{N}} \times \mathds{B}^n$. Theoretically speaking, such iterations of $F_f$ are thus a formal model of these kind of recurrent neural networks. In the rest of this -<<<<<<< HEAD paper, we will call such multilayer perceptrons ``CI-MLP($f$)'', which -======= -paper, we will call such multilayer perceptrons ``CI-MLP($f$)'', which ->>>>>>> 3df586d673bc4f3b32fa0dd1cb46796256744772 stands for ``Chaotic Iterations based MultiLayer Perceptron''. Checking if CI-MLP($f$) behaves chaotically according to Devaney's @@ -864,11 +860,7 @@ are compared. Thereafter we give, for the different learning setups and data sets, the mean prediction success rate obtained for each output. Such a rate -<<<<<<< HEAD represents the percentage of input-output pairs belonging to the test -======= -represents the percentage of input-output pairs belonging to the test ->>>>>>> 3df586d673bc4f3b32fa0dd1cb46796256744772 subset for which the corresponding output value was correctly predicted. These values are computed considering 10~trainings with random subsets construction, weights and biases initialization. @@ -964,10 +956,6 @@ configuration is always expressed as a natural number, whereas in the first one the number of inputs follows the increase of the Boolean vectors coding configurations. In this latter case, the coding gives a finer information on configuration evolution. -<<<<<<< HEAD -======= - ->>>>>>> 3df586d673bc4f3b32fa0dd1cb46796256744772 \begin{table}[b] \caption{Prediction success rates for configurations expressed with Gray code} \label{tab2} @@ -1020,11 +1008,7 @@ usually unknown. Hence, the first coding scheme cannot be used systematically. Therefore, we provide a refinement of the second scheme: each output is learned by a different ANN. Table~\ref{tab3} presents the results for this approach. In any case, whatever the -<<<<<<< HEAD considered feedforward network topologies, the maximum epoch number, -======= -considered feedforward network topologies, the maximum epoch number, ->>>>>>> 3df586d673bc4f3b32fa0dd1cb46796256744772 and the kind of iterations, the configuration success rate is slightly improved. Moreover, the strategies predictions rates reach almost 12\%, whereas in Table~\ref{tab2} they never exceed 1.5\%. Despite of @@ -1132,11 +1116,7 @@ be investigated too, to discover which tools are the most relevant when facing a truly chaotic phenomenon. A comparison between learning rate success and prediction quality will be realized. Concrete consequences in biology, physics, and computer science security fields -<<<<<<< HEAD will then be stated. -======= -will then be stated. ->>>>>>> 3df586d673bc4f3b32fa0dd1cb46796256744772 % \appendix{} -- 2.39.5