From: Michel Salomon <salomon@caseb.iut-bm.univ-fcomte.fr>
Date: Mon, 10 Oct 2011 14:38:46 +0000 (+0200)
Subject: Merge branch 'master' of ssh://bilbo.iut-bm.univ-fcomte.fr/chaos1
X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/chaos1.git/commitdiff_plain/c8f45a13d8b4d730baf96ab75e62c6b9b8575ea0

Merge branch 'master' of ssh://bilbo.iut-bm.univ-fcomte.fr/chaos1

Conflicts:
	main.tex

Groumpf
---

c8f45a13d8b4d730baf96ab75e62c6b9b8575ea0
diff --cc main.tex
index 49564db,5bd42bc..79209de
--- a/main.tex
+++ b/main.tex
@@@ -556,7 -556,7 +556,11 @@@ condition  $\left(S,(x_1^0,\dots,  x_n^
  \rrbracket^{\mathds{N}}  \times \mathds{B}^n$.
  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
@@@ -860,9 -860,9 +864,13 @@@ 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
 +predicted.   These values are  computed considering  10~trainings with
  random  subsets  construction,   weights  and  biases  initialization.
  Firstly, neural networks having  10 and 25~hidden neurons are trained,
  with   a  maximum   number  of   epochs  that   takes  its   value  in
@@@ -956,6 -948,7 +964,10 @@@ configuration is always expressed as  
  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}
@@@ -1008,7 -987,7 +1020,11 @@@ usually  unknown.   Hence, the  first  
  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
@@@ -1116,7 -1099,7 +1132,11 @@@ be investigated  too, to  discover whic
  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{}