X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/chaos1.git/blobdiff_plain/486652fa99fdbcf0992d32f910b729e648e33644..978058d192c5e6cceb4a0183e96de54c8b71c402:/authors_response.tex?ds=sidebyside

diff --git a/authors_response.tex b/authors_response.tex
index f6bcb54..52f85a3 100644
--- a/authors_response.tex
+++ b/authors_response.tex
@@ -26,9 +26,11 @@ Detailed changes and addressed issues in the revision of the paper
 "Recurrent Neural Networks and Chaos: Construction, \\
 Evaluation, and Prediction Ability" \\
 renamed in \\
-"Chaotic Neural Networks: Construction, Evaluation, and Prediction Ability"
+Neural Networks and Chaos: Construction, Evaluation of Chaotic Networks, \\
+and Prediction of Chaos with Multilayer Feedforward Networks"
 
-by Jacques M. Bahi, Jean-Fran\c{c}ois Couchot, Christophe Guyeux, and Michel Salomon
+by Jacques M. Bahi, Jean-Fran\c{c}ois Couchot, \\
+Christophe Guyeux, and Michel Salomon
 
 \bigskip
 \end{center}
@@ -52,7 +54,12 @@ considered and have led to modifications in the paper.
   
   {\it Our response}
 
-  To be completed
+  Indeed, our  contributions are twofold.  Firstly, we present  how to
+  construct chaotic neural networks, according to Devaney's definition
+  of chaos,  and we discuss  their evaluation. Secondly, we  study the
+  capacity  of  classical  multilayer  feedfoward neural  networks  to
+  predict chaotic data. To highlight clearly these contributions we
+  have changed the title of our paper, as said above.
 \item Please  explain the Line  242( "than chaotic iterations  Ff with
   initial  condition............" ) and  Line 298(  "investigate, when
   comparing neural networks and Devaney's chaos").
@@ -71,20 +78,28 @@ considered and have led to modifications in the paper.
  
   {\it Our response}
 
-  To be completed
+  We  have corrected  lines 402-405  (now lines  419-422)  as follows:
+  ``For all  those feedforward network topologies and  all outputs the
+  obtained  results for  the non-chaotic  case outperform  the chaotic
+  ones. Finally, the rates for  the strategies show that the different
+  feedforward networks are unable  to learn them.'' More generally, in
+  the whole paper the term feedforward has been added, when needed, to
+  clarify our discussion.
 \item Please  explain the  meanings of the  percentage in TABLE  I and
   TABLE II.
 
- {\it Our response}
+  {\it Our response}
 
-  To be completed
+  We  have explained how  the success  rates (percentage)  are computed
+  lines~405-407.
 \item Except  for prediction  success rates, in  order to  reflect the
   prediction ability, please add the analysis of the prediction errors
   for data sequence and diagram it.
 
  {\it Our response}
 
-  To be completed
+ We have added two figures (Figures~3 and 4) and some comments about them
+ lines~425-431. We hope that we have answered the reviewer remark.
 \end{enumerate}
 
 \begin{itemize}
@@ -107,6 +122,8 @@ considered and have led to modifications in the paper.
 
   {\it Our response}
 
+  As suggested by the reviewer the conclusion has been shortened and we
+  have presented those definitions differently.
 \end{enumerate}
 
 We are very grateful to the reviewers who, by their recommendations,