A Pruning Algorithm Based on Relevancy Index of Hidden Neurons Outputs
Journal Title: Engineering, Technology & Applied Science Research - Year 2016, Vol 6, Issue 4
Abstract
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.
Authors and Affiliations
S. Abid, M. Chtourou, M. Djemel
Recognition of Generalized Patterns by a Differential Polynomial Neural Network
A lot of problems involve unknown data relations, identification of which can serve as a generalization of their qualities. Relative values of variables are applied in this case, and not the absolute values, which can be...
A Review on Energy Efficient CMOS Digital Logic
Autonomy of power supply used in portable devices directly depends on energy efficiency of digital logic. This means that digital systems, beside high processing power and very complex functionality, must also have very...
Important Non-Wood Forest Products in Turkey: An Econometric Analysis
Wood resources obtained from forest and non-wood forest products (NWFP) have gained great importance recently as their economic values keeps increasing by the day. In this study, forecasting of Turkish Non-Wood Forest Pr...
Buckling of Hybrid Composite Carbon/Epoxy/Aluminum Plates with Cutouts
Structural instability becomes an important concern in the composite plate safe and reliable design. In this research, a resistance analysis is carried out on plates made of hybrid composite material with and without ell...
A Comparative Analysis of Classification Algorithms on Diverse Datasets
Data mining involves the computational process to find patterns from large data sets. Classification, one of the main domains of data mining, involves known structure generalizing to apply to a new dataset and predict it...