New deep recurrent hybrid artificial neural network for forecasting seasonal time series

Karahasan, Ozlem; Bas, Eren; Egrioglu, Erol

doi:10.1007/s41066-023-00445-3

Cited by 6 publications

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A new statistical training algorithm for a single multiplicative neuron model artificial neural network

Gul,

Egrioglu,

Bas

2024

Granul. Comput.

Self Cite

View full text Add to dashboard Cite

The single multiplicative neuron model has been frequently used by researchers in recent years, as it does not have a complex structure and does not include the hidden layer unit number problem, unlike many feed-forward arti cial neural network models. The model of single multiplicative neuron model arti cial neural networks does not have statistical assumptions just like in many arti cial neural network models. Random error term is not used in the mathematical model of single multiplicative neuron model arti cial neural networks. This situation is not acceptable considering that arti cial neural networks work with random samples. Based on this idea, for the rst time, by including a random error term in the single multiplicative neuron model arti cial neural network model, mathematical equations of likelihood functions are given for Normal, Cauchy, Logistic, Gumbel and Laplace distributions. A new statistical training algorithm is proposed to obtain optimal weights and bias values of the network. In the new training algorithm, particle swarm optimization proposed by Kennedy and Eberhart (1995) is used in maximizing likelihood functions. In the performance evaluation of the proposed method, Nasdaq and S&P500 time series in different years are analyzed and the analysis results are compared with many arti cial neural network models in the literature. Finally, it is concluded that the proposed method produces very successful forecasting results.

show abstract