A Modified Invasive Weed Optimization Algorithm for training of feed- forward Neural Networks

Invasive Weed Optimization Algorithm IWO) is an ecologically inspired metaheuristic that mimics the process of weeds colonization and distribution and is capable of solving multi-dimensional, linear and nonlinear optimization problems with appreciable efficiency. In this article a modified version of IWO has been used for training the feed-forward Artificial Neural Networks (ANNs) by adjusting the weights and biases of the neural network. It has been found that modified IWO performs better than another very competitive real parameter optimizer called Differential Evolution (DE) and a few classical gradient-based optimization algorithms in context to the weight training of feed-forward ANNs in terms of learning rate and solution quality. Moreover, IWO can also be used in validation of reached optima and in the development of regularization terms and non-conventional transfer functions that do not necessarily provide gradient information

[1]  W. Land,et al.  A new training algorithm for the general regression neural network , 1997, 1997 IEEE International Conference on Systems, Man, and Cybernetics. Computational Cybernetics and Simulation.

[2]  R. Storn,et al.  Differential evolution a simple and efficient adaptive scheme for global optimization over continu , 1997 .

[3]  Alireza Mallahzadeh,et al.  DESIGN OF AN E-SHAPED MIMO ANTENNA USING IWO ALGORITHM FOR WIRELESS APPLICATION AT 5.8 GHZ , 2009 .

[4]  K. N. Dollman,et al.  - 1 , 1743 .

[5]  Lifeng Xi,et al.  Evolving artificial neural networks using an improved PSO and DPSO , 2008, Neurocomputing.

[6]  Jin Xu,et al.  Application of a novel IWO to the design of encoding sequences for DNA computing , 2009, Comput. Math. Appl..

[7]  Laurene V. Fausett,et al.  Fundamentals Of Neural Networks , 1994 .

[8]  Aghil Yousefi-Koma,et al.  Optimal positioning of piezoelectric actuators on a smart fin using bio-inspired algorithms , 2007 .

[9]  Caro Lucas,et al.  A novel numerical optimization algorithm inspired from weed colonization , 2006, Ecol. Informatics.

[10]  X. Yao Evolving Artificial Neural Networks , 1999 .

[11]  Mahamed G. H. Omran,et al.  Global-best harmony search , 2008, Appl. Math. Comput..

[12]  Dong-Sun Kim,et al.  A Modified Genetic Algorithm for Fast Training Neural Networks , 2005, ISNN.

[13]  Leonard G. C. Hamey,et al.  XOR has no local minima: A case study in neural network error surface analysis , 1998, Neural Networks.

[14]  Udo Seiffert,et al.  Training of Large-Scale Feed-Forward Neural Networks , 2006, The 2006 IEEE International Joint Conference on Neural Network Proceedings.

[15]  Caro Lucas,et al.  A recommender system based on invasive weed optimization algorithm , 2007, 2007 IEEE Congress on Evolutionary Computation.

[16]  Zhen Zhu,et al.  Optimized Approximation Algorithm in Neural Networks Without Overfitting , 2008, IEEE Transactions on Neural Networks.

[17]  Henri Pierreval,et al.  Evolutionary approaches to the design and organization of manufacturing systems , 2003 .

[18]  Ke Chen,et al.  Applied Mathematics and Computation , 2010 .

[19]  Richard D. Neidinger,et al.  Neural networks from idea to implementation , 1995, APLQ.

[20]  Xudong Jiang,et al.  Constructing and training feed-forward neural networks for pattern classification , 2003, Pattern Recognit..

[21]  Wei Gao,et al.  Evolutionary Neural Network Based on New Ant Colony Algorithm , 2008, 2008 International Symposium on Computational Intelligence and Design.