A modular system which improves the topological maps

A system which permits the cooperation of a linear network with a topological map (TM) is proposed. It allows drastic reduction of the computing time for the TM. It is shown that the TM can be expressed as an adaptive gradient algorithm for the minimization of a cost function. Then, to train the hybrid architecture, new cost functions and algorithms are proposed. Convergence issues are discussed which allow considerations of generic problems in the general framework of multimodule architectures, and solutions are proposed. Some tests which illustrate the behavior and performance of the algorithms are presented.<<ETX>>

[1]  Sylvie Thiria,et al.  Cooperation of neural nets for robust classification , 1990, 1990 IJCNN International Joint Conference on Neural Networks.

[2]  J. Lampinen,et al.  Fast Computation of Kohonen Self-Organization , 1989, NATO Neurocomputing.

[3]  Patrick Gallinari,et al.  Learning vector quantization, multi layer perceptron and dynamic programming: comparison and cooperation , 1991, IJCNN-91-Seattle International Joint Conference on Neural Networks.

[4]  P. Gallinari,et al.  A speech recognizer optimally combining learning vector quantization, dynamic programming and multi-layer perceptron , 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[5]  L. E. Scales,et al.  Introduction to Non-Linear Optimization , 1985 .

[6]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory , 1988 .

[7]  Kumpati S. Narendra,et al.  Adaptation and learning in automatic systems , 1974 .

[8]  Hervé Bourlard.  HOW CONNECTIONIST MODELS COULD IMPROVE MARKOV MODELS FOR SPEECH RECOGNITION , 1990 .

[9]  Bernard Angéniol,et al.  Self-organizing feature maps and the travelling salesman problem , 1988, Neural Networks.

[10]  H. Bourlard,et al.  Links Between Markov Models and Multilayer Perceptrons , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  Patrick Gallinari,et al.  A Framework for the Cooperation of Learning Algorithms , 1990, NIPS.

[12]  P. Gallinari,et al.  A unified formalism for neural net training algorithms , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.