Dynamic topology generation of an artificial neural network of the multilayer perceptron type
This paper deals with an approximate constructive method to find architectures of artificial neuronal network (ANN) of the type Multi-Layer Percetron (MLP) which solves a particular problem. This method is supplemented with the technique of the Forced search of better local minima. The training of the net uses an algorithm basic descending gradient (BDG). Techniques such as repetition of the training and the early stopping (cross validation) are used to improve the results. The evaluation approach is based not only on the learning abilities but also on the generalization of the specific generated architectures of a domain. Experimental results are presented in order to prove the effectiveness of the proposed method. These are compared with architectures found by other methods.
J, Hilera. Redes Neuronales Artificiales. Fundamentos, modelos y aplicaciones. Alfaomega, MADRID 2000. p. 132-153.
K, Peng. “An algorithm to determine neural network hidden layer size and weight coefficients”. Proceedings of the 15th IEEE International Symposium on Intelligent Control (ISIC 2000). Rio Patras. Greece. 2000.
T. Yau. “Constructive Algorithms for structure learning in feedforward Neural Networks for Regression Problems”. IEEE Transactions on Neural Networks. Vol. XX. 1999. p. 16.
S. Ergeziner, E. Thomsen. “An accelerated learning algorthim for multilayer perceptions: optimization layer by layer”. IEEE Trans Neural Network. Vol 6. 1995. p 31-42.
F. M. Coetzee, V. L. Stonik. “Topology and geometry of single hidden layer network least square weight solution”. Neural Comput. Vol. 7. 1995. p 672-705.
L. M. Reynery. “Modified backpropagation algorithm for fast learning in neural networks”. Electron Left. Vol. 26. 1990. p. 10-18.
D. H. Park. “Novel fast training algorithm for multiplayer feedforward neural networks”. Electron. Left. Vol 26. 1992. pp. 1-100.
A. Sperduti. Staria A. “Speed up learning and network optimization with extended bacpropagation”. Neural Network, Vol 6. 1993. pp. 365-383.
T. Ash. “Dynamic node creation in back propagation networks”. Proceedings of Int. Conf. On Neural Networks. San Diego. 1989. pp. 365-375.
H. Hirose. “Back-propagation algorithm with varies the number of hidden units”. Neural Networks. Vol. 4, 1991. pp. 20-60.
S. Aylward, R. Anders. “An algorithm for neural network architecture generation”. A1AAA Computing in Aerospace VIII. Baltimore, 1991. p 30-90.
R. Tauel. Neural network with dynamically adaptable neurons. N94-29756, 1994. pp. 1-12
T. Masters, “Practical Neural Networks recipes in C++”. Ed. Academic Press, Inc. 1993. pp. 173-180.
X. Yao, “Evolving Artificial Neural Networks. School of Computer Science”. Proceedings IEEE. Septiembre, 1999.
E. Fiesler. “Comparative Bibliography of Ontogenic Neural Networks”. Proccedings of the International Conference on Artificial Neural Networks, ICANN 1994.
N. Murata, “Network Information Criterion-Determining the number oh hidden units for an Artificial Neural Network Model”. IEEE Trans. on Neural Networks. Vol. 5. 1994.
B. Martín del Brio, Redes Neuronales y Sistemas Difusos. AlfaOmega. 2002. pp. 64-66, 69.
V. Kurková. “Kolmogorov´s theorem and multiplayer neural networks”. Neural Networks. Vol. 5. 1992. pp. 501-506.
L. Prechelt. “Early Stopping – But When?”. Neural Networks: Tricks of the Trade. 1998. pp. 55-70.
D. Hush, B. Horner. “Progress in supervised neural networks: What´s new since Lipmman?”. IEEE Signal Proc. Mag., 1993.
L. Hwang, M. Maechler, S. Schimert, “Progression modeling in back-propagation and projection pursuit learning”. IEEE Transactions on Neural Networks. Vol. 5. 1994. pp. 342-353.
Copyright (c) 2006 Revista Facultad de Ingeniería Universidad de Antioquia
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Authors can archive the pre-print version (i.e., the version prior to peer review) and post-print version (that is, the final version after peer review and layout process) on their personal website, institutional repository and / or thematic repository
- Upon acceptance of an article, it will be published online through the page https://revistas.udea.edu.co/index.php/ingenieria/issue/archive in PDF version with its correspondent DOI identifier
The Revista Facultad de Ingeniería -redin- encourages the Political Constitution of Colombia, chapter IV
Chapter IV Sanctions 51
The following shall be liable to imprisonment for two to five years and a fine of five to 20 times the legal minimum monthly wage: (1) any person who publishes an unpublished literary or artistic work, or part thereof, by any means, without the express prior authorization of the owner of rights; (2) any person who enters in the National Register of Copyright a literary, scientific or artistic work in the name of a person other than the true author, or with its title altered or deleted, or with its text altered, deformed, amended or distorted, or with a false mention of the name of the publisher or phonogram, film, videogram or software producer; (3) any person who in any way or by any means reproduces, disposes of, condenses, mutilates or otherwise transforms a literary, scientific or artistic work without the express prior authorization of the owners thereof; (4) any person who reproduces phonograms, videograms, software or cinematographic works without the express prior authorization of the owner, or transports, stores, stocks, distributes, imports, sells, offers for sale, acquires for sale or distribution or in any way deals in such reproductions. Paragraph. If either the material embodiment or title page of or the introduction to the literary work, phonogram, videogram, software or cinematographic work uses the name, business style, logotype or distinctive mark of the lawful owner of rights, the foregoing sanctions shall be increased by up to half.