Login Form
Visitors Counter
Today | 24 | |
Yesterday | 46 | |
This week | 112 | |
This month | 84 | |
All | 195248 |
Who's Online
We have 5 guests online- Error
Improving the classification efficiency of an ANN utilizing a new training methodology |
I.E. Livieris. Improving the classification efficiency of an ANN utilizing a new training methodology. Informatics, 2018.
Abstract - In this work, a new approach for training artificial neural networks is presented which utilizes techniques for solving the constraint optimization problem. More specifically, this study converts the training of a neural network into a constraint optimization problem. Furthermore, we propose a new neural network training algorithm based on L-BFGS-B method. Our numerical experiments illustrate the classification efficiency of the proposed algorithm and of our proposed methodology, leading to more efficient, stable and robust predictive models. |