Search Results - subject:"Training algorithms"

On the use of back propagation and radial basis function neural networks in surface roughness prediction

Markopoulos, Angelos P.; Georgiopoulos, Sotirios; … - In: Journal of Industrial Engineering International 12 (2016), pp. 389-400

Various artificial neural networks types are examined and compared for the prediction of surface roughness in manufacturing technology. The aim of the study is to evaluate different kinds of neural networks and observe their performance and applicability on the same problem. More specifically,...

Persistent link: https://www.econbiz.de/10011640900

On the use of back propagation and radial basis function neural networks in surface roughness prediction

Markopoulos, Angelos P.; Georgiopoulos, Sotirios; … - In: Journal of industrial engineering international 12 (2016), pp. 389-400

Persistent link: https://www.econbiz.de/10011563692

Impact of artificial neural networks training algorithms on accurate prediction of property values

Yacim, Joseph Awoamim; Boshoff, Douw Gert Brand - In: The journal of real estate research 40 (2018) 3, pp. 375-418

Persistent link: https://www.econbiz.de/10011943000

Comparative Study of Artificial Neural Networks and Wavelet Artificial Neural Networks for Groundwater Depth Data Forecasting with Various Curve Fractal Dimensions

He, Zhenfang; Zhang, Yaonan; Guo, Qingchun; Zhao, Xueru - In: Water Resources Management 28 (2014) 15, pp. 5297-5317

series data. Three types of training algorithms for ANN and WANN models using a Mallat decomposition algorithm were …

Persistent link: https://www.econbiz.de/10011151765

River Suspended Sediment Prediction Using Various Multilayer Perceptron Neural Network Training Algorithms—A Case Study in Malaysia

Mustafa, M.; Rezaur, R.; Saiedi, S.; Isa, M. - In: Water Resources Management 26 (2012) 7, pp. 1879-1897

training algorithms are Gradient Descent (GD), Gradient Descent with Momentum (GDM), Scaled Conjugate Gradient (SCG), and … accuracy were used to evaluate the performance of training algorithms. The analysis showed that SCG and LM performed better … shorter time of convergence. It was concluded that both training algorithms SCG and LM could be recommended for suspended …

Persistent link: https://www.econbiz.de/10010997800