Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network
Apstrakt
Neurons in an artificial neural network are grouped in three layers: input, output and hidden layer. Determination of an optimal number of neurons in hidden layer is one of the major difficulties in the process of creating artificial neural network topology. The main goal of this paper is to explore and compare existing methods for determining number of hidden neurons. The research is conducted on two separate datasets with different number of input values and different number of training pairs.
Ključne reči:
test error / methods / hidden neurons / comparison / artificial neural networksIzvor:
Central European Conference on Information and Intelligent Systems (CECIIS 2016), 2016, 219-223Izdavač:
- Fac Organization And Informatics, Univ Zagreb, Varazdin
Finansiranje / projekti:
- LAMS (Lightning Activity Monitoring System) project
Institucija/grupa
Fakultet organizacionih naukaTY - CONF AU - Vujicić, Tijana AU - Matijević, Tripo AU - Ljucović, Jelena AU - Balota, Adis AU - Ševarac, Zoran PY - 2016 UR - https://rfos.fon.bg.ac.rs/handle/123456789/1491 AB - Neurons in an artificial neural network are grouped in three layers: input, output and hidden layer. Determination of an optimal number of neurons in hidden layer is one of the major difficulties in the process of creating artificial neural network topology. The main goal of this paper is to explore and compare existing methods for determining number of hidden neurons. The research is conducted on two separate datasets with different number of input values and different number of training pairs. PB - Fac Organization And Informatics, Univ Zagreb, Varazdin C3 - Central European Conference on Information and Intelligent Systems (CECIIS 2016) T1 - Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network EP - 223 SP - 219 UR - conv_2419 ER -
@conference{ author = "Vujicić, Tijana and Matijević, Tripo and Ljucović, Jelena and Balota, Adis and Ševarac, Zoran", year = "2016", abstract = "Neurons in an artificial neural network are grouped in three layers: input, output and hidden layer. Determination of an optimal number of neurons in hidden layer is one of the major difficulties in the process of creating artificial neural network topology. The main goal of this paper is to explore and compare existing methods for determining number of hidden neurons. The research is conducted on two separate datasets with different number of input values and different number of training pairs.", publisher = "Fac Organization And Informatics, Univ Zagreb, Varazdin", journal = "Central European Conference on Information and Intelligent Systems (CECIIS 2016)", title = "Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network", pages = "223-219", url = "conv_2419" }
Vujicić, T., Matijević, T., Ljucović, J., Balota, A.,& Ševarac, Z.. (2016). Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network. in Central European Conference on Information and Intelligent Systems (CECIIS 2016) Fac Organization And Informatics, Univ Zagreb, Varazdin., 219-223. conv_2419
Vujicić T, Matijević T, Ljucović J, Balota A, Ševarac Z. Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network. in Central European Conference on Information and Intelligent Systems (CECIIS 2016). 2016;:219-223. conv_2419 .
Vujicić, Tijana, Matijević, Tripo, Ljucović, Jelena, Balota, Adis, Ševarac, Zoran, "Comparative Analysis of Methods for Determining Number of Hidden Neurons in Artificial Neural Network" in Central European Conference on Information and Intelligent Systems (CECIIS 2016) (2016):219-223, conv_2419 .