A Pruning Algorithm Based on Relevancy Index of Hidden Neurons Outputs

Choosing the training algorithm and determining the architecture of artificial neural networks are very important issues with large application. There are no general methods which permit the estimation of the adequate neural networks size. In order to achieve this goal, a pruning algorithm based on the relevancy index of hidden neurons outputs is developed in this paper. The relevancy index depends on the output amplitude of each hidden neuron and estimates his contribution on the learning process. This method is validated with an academic example and it is tested on a wind turbine modeling problem. Compared with two modified versions of Optimal Brain Surgeon (OBS) algorithm, the developed approach gives interesting results.

Identification and Optimization of Recombinant E. coli Fed-Batch Fermentation Producing γ-Interferon Protein

A novel approach to identification of fed-batch cultivation of E. coli BL21 (DE3) has been presented. The process has been identified in the system that is designed for maximum production of γ-interferon protein. Dynamic order of the process has been determined by Lipschitz test. Multilayer Perceptron neural network has been used to process identification by experimental data. The optimal brain surgeon method is used to reduce the model complexity that can be easily implemented. Validation results base on autocorrelation function of the residuals, show good performance of neural network and make it possible to use of it in process analyses.