Two novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochastic

Yükleniyor...
Küçük Resim

Tarih

2017-11-13

Dergi Başlığı

Dergi ISSN

Cilt Başlığı

Yayıncı

Springer Nature

Erişim Hakkı

info:eu-repo/semantics/closedAccess
Attribution-NonCommercial-ShareAlike 3.0 United States

Özet

Although high accuracies were achieved by artificial neural network (ANN), determining the optimal number of neurons in the hidden layer and the activation function is still an open issue. In this paper, the applicability of assigning the number of neurons in the hidden layer and the activation function randomly was investigated. Based on the findings, two novel versions of randomized ANNs, which are stochastic, and pruned stochastic, were proposed to achieve a higher accuracy without any time-consuming optimization stage. The proposed approaches were evaluated and validated by the basic versions of the popular randomized ANNs [1] are the random weight neural network [2], the random vector functional links [3] and the extreme learning machine [4] methods. In the stochastic version of randomized ANNs, not only the weights and biases of the neurons in the hidden layer but also the number of neurons in the hidden layer and each activation function were assigned randomly. In pruned stochastic version of these methods, the winner networks were pruned according to a novel strategy in order to produce a faster response. Proposed approaches were validated via 60 datasets (30 classification and 30 regression datasets). Obtained accuracies and time usages showed that both versions of randomized ANNs can be employed for classification and regression.

Açıklama

Anahtar Kelimeler

Extreme Learning Machines, Pruned Stochastic, Random Activation Function, Random Network Structure, Random Vector Functional Link, Randomized Weight Neural Network, Stochastic

Kaynak

WoS Q Değeri

Q2

Scopus Q Değeri

Q2

Cilt

48

Sayı

1

Künye

Ertuğrul, Ö F. (2017). Two novel versions of randomized feed forward artificial neural networks: Stochastic and pruned stochastic. Neural Processing Letters, 48(1), pp. 481-516. https://doi.org/10.1007/s11063-017-9752-x