Optimization of Neural Networks with Response Surface Methodology: Prediction of Cigarette Pressure Drop

Midilli, Yunus Emre; Elevli, Sermin

doi:10.1109/itms47855.2019.8940643

Cited by 2 publications

(1 citation statement)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are various methodologies applied in the literature to optimise the hyperparameters of neural networks: simulated annealing [16], genetic algorithms [17], particle swarm optimization [18] etc. Apart from the evolutionary algorithms, design of experiments, which is a statistical technique, has also been used [19]. In the research of [20], exponential smoothing transition autoregressive time series is used for prediction.…”

Section: Literature Reviewmentioning

confidence: 99%

Design of Experiments vs. TOPSIS to Select Hyperparameters of Neural Attention Models in Time Series Prediction

Midilli

Parshutin

2020

ITMS

Self Cite

View full text Add to dashboard Cite

Attention models are used in neural machine translation to overcome the challenges of classical encoder-decoder models. In the present research, design of experiments and TOPSIS methods are used to select hyperparameters of a neural attention model for time series prediction. The configurations selected by both methods are compared with out-of-sample data in time interval between January 2020 and April 2020 when global economies were significantly impacted due to Covid-19 pandemic. Results demonstrated that both selection methods outperformed each other in terms of different output features. On the other hand, our results with more than 95 % coefficient of determination and less than 0.23 % MAPE verified that neural attention models had strong capabilities in exchange rate prediction even in extraordinary situations in global economies.

show abstract