. La-détermination-de-l, état interne désiré s'(t) est réalisée par un algorithme qui rappelle celui de la rétro-propagation des états désirés [Le Cun 87c

. Où-j-est-un-neurone-prédecesseur-du-neurone-i,-k-est-une-constante, wij est le poids de la connexion entre le neurone j et le neurone i, pour les neurones de sortie : ei = (xdi -xi), xdi est la valeur d'activation désirée

N. Est-un-nombre-d-'itérations-qui-devrait-Être-infini, En effet, le nombre d'itérations nécessaires à la convergence de l'algorithme de la rétropropagation n'est pas connu. On le fixe arbitrairement. De ce fait, on court le risque de croire que le problème est de nature séquentiel

]. L. Almeida-88 and . Almeida, Backpropagation in Perceptrons with Feedback, NATO ASI Series, 1988.
DOI : 10.1007/978-3-642-83740-1_22

E. Chappaz and N. Giambiasi, STALINN : Statistical module for Testing Learning phase In Neural Nets, Neuro-Nîmes, vol.88, 1988.

E. Decamp and B. Amy, Neurocalcul et réseaux d'automates, le point sur les recherches et les applications, 1989.

]. S. Dehaene, J. Dehaene, and J. P. Changeux, Neural networks that learn temporal sequences by selection., Proceedings of the National Academy of Sciences, vol.84, issue.9, pp.2727-2731, 1987.
DOI : 10.1073/pnas.84.9.2727

J. L. Elman, S. I. Gallant, and D. J. King, Finding Structure in Time Center for Research in Language Technical Report 8801, University of CaliforniaExperiments With Sequential Associative Memories, Conf. Cognitive Science Society, 1988.

M. Gori, An Extension of BPS, Neuro-Nîmes, vol.89, pp.83-93, 1989.

J. Hartmanis and R. E. Stearns, Algebraic Structure Theory of Sequential Machines, Prentice-Hall International series in Applied MathematicsThe Organization of Behavior, 1949.

N. Hecht-nielsen, ANZA Plus : User's Guide and Neurosoft Documents, 1989.

]. M. Jordan, Serial Order: A Parallel Distributed Processing Approach, ICS Report, vol.8604, 1986.
DOI : 10.1016/S0166-4115(97)80111-2

]. M. Jordan, Supervised learning and systems with excess degrees of freedom, 1988.

. Le-cun-87a-]-y and . Le-cun, Modèles Connexionnistes de l'Apprentissage, Thèse de

. Le-cun-87b-]-y and . Le-cun, Modèles Connexionnistes de l'Apprentissage, Thèse de

. Le-cun-87c-]-y and . Le-cun, Modèles Connexionnistes de l'Apprentissage, Thèse de

]. Y. Liu, G. Z. Sun, H. H. Chen, and Y. C. Lee, Grammatical inference and neural network state machines, Proceedings of IJCNN 89, 1990.

R. Lippmann, An introduction to computing with neural nets, IEEE ASSP Magazine, 1987.

J. L. Mc-clelland and D. E. Rumelhart, Explorations in Parallel Distributed Processing, a Handbook of Models, programs, and Exercices, 1988.

M. L. Minsky and S. A. Paper, Perceptrons Expanded EditionSequential Learning : Observation on the Internal Code Generation Problem, Proceedings of the 1988 Connectionist Models Summer School, 1988.

B. A. Pearlmutter, Learning State Space Trajectories in Recurrent Neural Networks CMU-CS-88-191, 1988.

]. F. Pineda-87 and . Pineda, Generalization of back-propagation to recurrent neural networks, Physical Review Letters, vol.59, issue.19, 1987.
DOI : 10.1103/PhysRevLett.59.2229

]. F. Pineda, Recurrent Back-Propagation and the Dynamical Approach to

D. E. Rumelhart, G. E. Hinton, and R. Williams, Learning internal representations by error propagation," dans "Parallel Distributed Processing : Explorations in the Microstructure of Cognition, Foundations, vol.1, 1986.

R. Rohwer and S. Renals, Training Recurrent NetworksShort-term memory/Long-term memory interactions in connectionist simulations of psychological experiments on list learning, Proceedings of nEURO 88, Personnaz L. and Dreyfus G. Eds, ESPCI Proceedings of nEURO 88, Personnaz L. and Dreyfus G. Eds, ESPCI, 1988.

T. Sejnowski and C. Rosenberg, NETtalk : a parallel network that learns to read aloud, p.32, 1986.

D. Servan-schreiber, A. Cleeremans, and J. L. Mcclelland, Encoding sequential structure in simple recurrent networks CMU-CS-88-183Encoding sequential structure: experience with real-time recurrent learning algorithm, Proceedings of IJCNN 89, 1988.

P. Todd, A Sequential Network Design for Musical Application, Proceedings of the 1988 Connectionist Models Summer School

C. Touzet and N. Giambiasi, Reconnaissance de séquences par des réseaux de neurones, Neuro-Nîmes, vol.88, pp.383-394, 1988.

]. C. Touzet-89a, N. Touzet, and . Giambiasi, Neuromimetic Sequential Machines, IASTED expert systems, pp.26-28, 1989.

]. C. Touzet-90a, N. Touzet, and . Giambiasi, Connectionist finite-state machines, Proceedings of IJCNN 1990, pp.15-19, 1990.

]. C. Touzet-90b, N. Touzet, and . Giambiasi, Quelques approches neuromimétiques pour le traitement des séquences, 1990.

. Fu-sheng, G. W. Tsung, and . Cottrell, A sequential adder using recurrent networks, Proceedings of IJCNN 89, 1989.

R. L. Watrous, Phoneme discrimination using connectionist networks, The Journal of the Acoustical Society of America, vol.87, issue.4, 1989.
DOI : 10.1121/1.399424

]. R. Williams and D. Zipser, A Learning Algorithm for Continually Running Fully Recurrent Neural Networks, Neural Computation, vol.11, issue.2, 1988.
DOI : 10.1016/0885-064X(88)90021-0