Gauss-Newton approximation to Bayesian learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

A Deep CNN-LSTM Model for Particulate Matter (PM2.5) Forecasting in Smart Cities (2018, background): “However, there are many ways to avoid overfitting, such as regularization [28], data augmentation [22], dropout [29], dropconnect [30], or early stopping [31].”
Neural network models to predict cation exchange capacity in arid regions of Iran (2005, methodology): “…MSEReg, in which the sum of network weights is added to the MSE: MSEReg ¼ MSEþ ð1 ÞMSW; ð5Þ where is a performance ratio calculated by means of the Bayesian regularization in combination with the Levenberg– Marquardt algorithm (Foresee & Hagan, 1997), and MSW is the mean of the squared weights.”
Freeway Travel Time Prediction with State-Space Neural Networks: Modeling State-Space Dynamics with Recurrent Neural Networks (2002, background): “For a comprehensive treatment of these techniques, see elsewhere ( 23, 24 ).”
Accurate freeway travel time prediction with state-space neural networks under missing data (2005, methodology): “Details on the algorithms used (Levenberg–Marquardt and Bayesian Regularization LM–BR) can be found in Hagan and Menhaj (1994) and Foresee and Hagan (1997) respectively.”