Studying the Effect of Optimizing Weights in Neural Networks with Meta-Heuristic Techniques

Autor:	Nazri Mohd Nawi, Jamal Uddin, M. Z. Rehman, Rashid Naseem, Abdullah Ayub Khan
Rok vydání:	2019
Předmět:	Artificial bee colony algorithm Levenberg–Marquardt algorithm Recurrent neural network Artificial neural network Search algorithm Computer science Computer Science::Neural and Evolutionary Computation Feedforward neural network Cuckoo search Algorithm Backpropagation
Zdroj:	Proceedings of the International Conference on Data Engineering 2015 (DaEng-2015) ISBN: 9789811317972 DaEng
Popis:	Meta-heuristic algorithms provide derivative-free solutions to optimize complex problems. Back-propagation Neural Network (BP) algorithm is one of the most commonly used and a popular technique to optimize the feed forward neural network training. Traditional BP algorithm has some drawbacks, such as getting stuck easily in local minima and slow speed of convergence. This paper proposed a new meta-heuristic search algorithm, called cuckoo search (CS), based on cuckoo bird’s behavior to train back propagation (BP), Elman Recurrent Neural Network (RNN), and Levenberg Marquardt (LM) algorithms to achieving fast convergence rate and to avoid local minima problem. The performances of the proposed hybrid Cuckoo Search algorithms are compared with artificial bee colony using BP algorithm, and other hybrid variant. Specifically on Iris and 7-Bit parity datasets are used. The simulation results show that the hybrid Cuckoo Search show better performances than the other hybrid technique.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::36d63efe50fc7515594f8fc106adf333 https://doi.org/10.1007/978-981-13-1799-6_34 Zobrazit plný text záznamu