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
Keywords
Related Articles
- EP ID EP109679
- DOI -
- Views 273
- Downloads 0
Comparison of Mechanical Properties of Lightweight and Normal Weight Concretes Reinforced with Steel Fibers
Compared to conventional concrete, lightweight concrete is more brittle in nature however, in many situations its application is advantageous due to its lower weight. The associated brittleness issue can be, to some exte...
Petrophysical Evaluation of the Sarvak Formation Based on Well Logs in Dezful Embayment, Zagros Fold Zone, South West of Iran
Dezful embayment in the south west of Iran is part of Zagros fold zone which despite the small area includes almost all of Iran oil production. Sarvak Formation with middle cretaceous (Albin-Turunin) is the second bigges...
Security Analysis of Zipper Hash Against Multicollisions Attacks
In this paper, the existence of multicollisions in Zipper Hash structure, a new Hash structure which was introduced to strengthen the iterated Hash structures, is presented. This study shows that finding multicollisions...
Evaluation of Three Common Algorithms for Structure Active Control
Recently active structure controllers were considered to deal with the impact of earthquake forces and the result of the investigations provided multiple algorithms to calculate force control and many different ways to a...
Forecast on 2030 Vietnam Electricity Consumption
The first but very significant step in electricity system planning is to make an accurate long-term forecast on electricity consumption. This article aims to forecast the consumption for the Vietnam electricity system (G...