Abstract
Prior knowledge of the input–output problems often leads to supervised learning restrictions that can hamper the multi-layered perceptron’s (MLP) capacity to find an optimal solution. Restrictions such as fixing weights and modifying input variables may influence the potential convergence of the back-propagation algorithm. This paper will show mathematically how to handle such constraints in order to obtain a modified version of the traditional MLP capable of solving targeted problems. More specifically, it will be shown that fixing particular weights according to prior information as well as transforming incoming inputs can enable the user to limit the MLP search to a desired type of solution. The ensuing modifications pertaining to the learning algorithm will be established. Moreover, four supervised improvements will offer insight on how to control the convergence of the weights towards an optimal solution. Finally, applications involving packing and covering problems will be used to illustrate the potential and performance of this modified MLP.
Similar content being viewed by others
References
Kolean JF, Hewett R (2000) Prediction of lake inflows with neural networks. In: 2000 IEEE international conference on systems, man, and cybernetics, vol. 1, pp 572–576
Perez CA, Gonzalez GD, Salinas C (2001) Genetic selection of non-linear product terms in the inputs to a linear classifier for handwritten digit recognition. In: 2001 IEEE international conference on systems man and cybernetics, vol. 4, pp 2337–2342
Kamiura N, Taniguchi Y, Matsui N (2001) A functional manipulation for improving tolerance against multiple-valued weight faults of feed-forward neural networks. In: 2001 Proceedings 31st IEEE international symposium on multiple-valued logic, pp 339–344
Flake GW (1998) Square unit augmented, radially extended, multilayer perceptrons. In: Orr GB, Milllet K-R (eds) Neural networks: tricks of the trade. vol. 1524 of Lecture Notes in Computer Science. Springer, Berlin Heidelberg New York, pp 145–163
Rumelhart DE, McClelland JL and the PDP Research Group (1986) Parallel distributed processing: exploration in the microstructure of cognition, vol. 2. MIT, Cambridge
Lee YC, Doolen G, Chen HH, Sun GZ, Maxwell T, Lee HY, Giles CL (1986) Machine learning using higher order correlation networks. Physica D 22(D):276–306
Pao YH (1989) Adaptive pattern recognition and neural networks. Addison-Wesley, Reading
Rogers CA (1964) Packing and covering, Cambridge University Press, Cambridge
Zong C (1999) Sphere packing. Springer, Berlin Heidelberg New York
Conway JH, Sloan NJA (1993) Sphere packing, lattices and groups, second edition. Springer, Berlin Heidelberg New York
Jacob E. Goddman, Joseph O’Rourke (2004) Handbook of discrete and computational geometry. CRC Press, Boca Raton
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Labib, R., Assadi, R. Modified multi-layered perceptron applied to packing and covering problems. Neural Comput & Applic 16, 173–186 (2007). https://doi.org/10.1007/s00521-006-0064-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-006-0064-8