European Symposium on Artificial Neural Networks ESANN'2001 159 Multiple Layer Perceptron Training Using Genetic Algorithms
Abstract:
Multiple Layer Perceptron networks trained with backpropagation algorithm are very frequently used to solve a wide variety of real-world problems. Usually a gradient descent algorithm is used to adapt the weights based on a comparison between the desired and actual network response to a given input stimulus. All training pairs, each consisting of input vector and desired output vector, are forming a more or less complex multi-dimensional error surface during the training process. Numerous suggestions have been made to prevent the gradient descent algorithm from becoming captured in any local minimum when moving across a rugged error surface. This paper describes an approach to substitute it completely by a genetic algorithm. By means of some benchmark applications characteristic properties of both the genetic algorithm and the neural network are explained. 1
Citations
| 2141 | Learning Internal Representations by Error Propagation – Rumelhart, Hinton, et al. - 1986 |
| 1827 | Adaptation in nature and artificial system – Holland - 1992 |
| 363 | Perceptrons: An Introduction To Computational Geometry – Minsky, Papert - 1969 |
| 159 | An evolutionary algorithm that constructs recurrent neural networks – Angeline, Saunders, et al. - 1993 |
| 39 | Evolutionary algorithms for neural network design and training – Branke - 1995 |
| 12 | Neural Network Training using Genetic Algorithms, World Scientific – Rooij, Jain, et al. - 1996 |
| 11 | Properties of genetic representations of neural architectures – Balakrishnan, Honavar - 1995 |
| 7 | Use of genetic algorithms for optimal topology determination in back propagation neural networks – Robbins, Soper, et al. - 1993 |
| 5 | Practical approach to pattern recognition – Batchelor - 1974 |
| 3 | Three-dimensional quasi-binary image restoration for confocal microscopy and its application to dendritic trees – Herzog, Krell, et al. - 1997 |
