每年出版 12 期
ISSN 打印: 0040-2508
ISSN 在线: 1943-6009
Indexed in
A Growing Cell Neural Network Structure with Backpropagation Learning Algorithm
摘要
A classical model used for pattern recognition is the Multilayer Perceptron Artificial Neural Network (ANN), with backpropagation learning algorithm. However the recognition performance of this ANN strongly depends on the number of neurons used in the hidden layer, is a function of the particular problem to be solved. Then, in most cases this number is unknown in advance. A possible solution for this problem may be the use of growing cells structures, such as those used in the solution of some classification problems with auto organizing ANN. Using a similar idea, we propose a growing cell multilayer ANN in which a modified backpropagation algorithm is used to optimize the ANN weights matrix, as well as the number of neurons in the hidden layer. A proposed approach also reduces the computational complexity of conventional multilyer perceptron with backpropagation learning algorithms during the training stage, using at the beginning a reduced number of neurons in the hidden layer to minimize the identification error. This number is then increased until reach its optimal size. The proposed structure was evaluated with some benchmarks problems such as XOR, four different classes classification and ZIGZAG problems.
-
Sotos Jorge Mateo, Arnau Jose Manuel Blas, Aranda Ana Maria Torres, Melendez Cesar Sanchez, Removal of Muscular and Artefacts Noise from the ECG by a Neural Network, 2007 5th IEEE International Conference on Industrial Informatics, 2007. Crossref
-
Mateo J., Sanchez C., Vaya C., Cervigon R., Rieta J.J., A new adaptive approach to remove baseline wander from ECG recordings using Madeline structure, 2007 Computers in Cardiology, 2007. Crossref