2 \documentclass{article}
3 \usepackage[T1]{fontenc}
4 \usepackage[latin1]{inputenc}
7 \renewcommand{\labelenumii}{\labelenumi\arabic{enumii}}
15 \vspace{-0.5cm}\hspace{-2cm}Computer Science Laboratory, LIFC
17 \hspace{-2cm}University of Franche-Comt\'e
19 \hspace{-2cm}25030 Besan\c{c}on, France.
24 Detailed changes and addressed issues in the revision of the paper
26 "Recurrent Neural Networks and Chaos: Construction, \\
27 Evaluation, and Prediction Ability" \\
29 "Chaotic Neural Networks: Construction, Evaluation, and Prediction Ability"
31 by Jacques M. Bahi, Jean-Fran\c{c}ois Couchot, Christophe Guyeux, and Michel Salomon
36 Please, find below the detailed changes and issues we addressed in the
37 revision of our above mentioned paper that we resubmit.
39 All the remarks and recommendations of the three reviewers have been
40 considered and have led to modifications in the paper.
43 \item Concerning the remarks of reviewer No. 1:
47 \item Please explain the topic "Recurrent Neural Networks and Chaos:
48 Construction, Evaluation, and Prediction Ability" which makes me
49 confused. Does the paper discuss the construction, evaluation, and
50 prediction ability of chaotic neural networks? And in the paper, the
51 chaotic neural networks are mainly done research on.
56 \item Please explain the Line 242( "than chaotic iterations Ff with
57 initial condition............" ) and Line 298( "investigate, when
58 comparing neural networks and Devaney's chaos").
63 \item Section VI analyzes the suitability of artificial neural
64 networks for predicting chaotic behaviors. So, I think section VI
65 don't correspond to the topic. And homoplastically, lines 30-32("the
66 learning, with neural networks having a feedforward structure, of
67 chaotic behaviors represented by data sets obtained from chaotic
68 maps, is far more difficult than non chaotic behaviors") refer to
69 the learning of neural networks having a feedforward structure. But
70 lines 402-405 refer to all the network topologies.
75 \item Please explain the meanings of the percentage in TABLE I and
81 \item Except for prediction success rates, in order to reflect the
82 prediction ability, please add the analysis of the prediction errors
83 for data sequence and diagram it.
91 \item Concerning the remarks of reviewer No. 2:
95 \item On the basis of the result botained by Guyeux in Ref[12], the
96 authors dealed with chaotic neural networks for various fields of
97 appli1cation. Firstly, the authors described how to build a neural
98 network that can be trained to learn a given chaotic map function,
99 then found a condition that allow to check whether the iterations
100 induced by a function are chaotic or not, and thus if a chaotic map
101 is obtained. As the authors said that this work is different from
102 most of prviews works, this manuscript gave a rigorous mathematical
103 proof for chaos of chaotic neural networks. This is a very
104 interesting work. On the other hand, I think, the conclusion is too
105 long, and some Definitions such as Definition 1-Definition 5 are
106 wellknow Definition, it's no necessary to be presented any more.
112 We are very grateful to the reviewers who, by their recommendations,
113 allowed us to improve our paper.
116 %\TeXButton{Flushright}{\begin{flushright}