Title :
Pruning approaches for selection of neural networks structure
Author :
Abid, Sabeur ; Chtourou, Mohamed ; Djemel, Mohamed
Author_Institution :
Control & Energy Manage. Lab. (CEM Lab.), Univ. of Sfax, Sfax, Tunisia
Abstract :
Topology design of artificial neural networks (ANNs) is a complex problem. This paper presents a study of some approaches which derived from a pruning technique (OBS). In the first step, we explicit the corresponding algorithms used to determine the adequate number of neurons and weights for neural structure. In the second step, a comparative study of the presented strategies is also investigated according to numerical simulation example.
Keywords :
neural nets; numerical analysis; ANN; OBS algorithm; artificial neural networks; neural networks structure selection; numerical simulation; pruning approaches; Algorithm design and analysis; Biological neural networks; Equations; Mathematical model; Neurons; Optimization methods; Training; Neural network; OBS algorithm; neural structure; pruning methods;
Conference_Titel :
Systems, Signals & Devices (SSD), 2013 10th International Multi-Conference on
Conference_Location :
Hammamet
Print_ISBN :
978-1-4673-6459-1
Electronic_ISBN :
978-1-4673-6458-4
DOI :
10.1109/SSD.2013.6564137
