1-7 of 7
Keywords: hyperparameter
Close
Follow your search
Access your saved searches in your account

Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Proceedings Papers

Paper presented at the 57th U.S. Rock Mechanics/Geomechanics Symposium, June 25–28, 2023
Paper Number: ARMA-2023-0453
... to improve the quantity and quality of training data and to optimize the hyperparameters of the SVRM. Second, the enhanced training data are used to train the SVRM that predicts the Shmin based on the wellbore breakout geometries. In order to examine the reliability of this technique, the Shmin predicted...
Proceedings Papers

Paper presented at the 56th U.S. Rock Mechanics/Geomechanics Symposium, June 26–29, 2022
Paper Number: ARMA-2022-0822
... drilling fluid formulation drilling fluid property elkatatny abdulraheem hyperparameter accuracy artificial intelligence machine learning abdelaal baker hughe decision tree learning drilling fluid management & disposal drilling fluid chemistry rheology drilling drilling parameter mfv...
Proceedings Papers

Paper presented at the 56th U.S. Rock Mechanics/Geomechanics Symposium, June 26–29, 2022
Paper Number: ARMA-2022-0143
... model uses the back-propagation algorithm to achieve the training purpose. The parameters are mainly updated by obtaining the partial derivatives of the loss function for each weight parameter. The training process needs to set the hyperparameters, such as the learning rate, learning decay rate, sample...
Proceedings Papers

Paper presented at the 56th U.S. Rock Mechanics/Geomechanics Symposium, June 26–29, 2022
Paper Number: ARMA-2022-0142
... refers to the model selection, in which we adjust the parameters for a given classification problem to find the optimal value (known as hyper-parameters). Classically, three main hyperparameters in RF demand adjustments: max_features, n_estimators and min_sample_leaf. By verifying the performance...
Proceedings Papers

Paper presented at the 56th U.S. Rock Mechanics/Geomechanics Symposium, June 26–29, 2022
Paper Number: ARMA-2022-0358
... porosity and Vp). Based on the collected logging data set, the GRU prediction model for predicting Vs is trained, validated and tested, which can predict Vs in the missing sections according to synthetic logging data and depth correlation. The optimal hyperparameters of the proposed model, including...

Product(s) added to cart

Close Modal