Artificial Neural Networks Using Regularized Logistic Regression Cost Function: A Robust Lithofacies Classifier

In the past decade, a lot of progress in the field of Artificial Intelligence have been made in developing classification models to cater the needs of Geophysical Data Processing. This paper focuses on the application of regularization of the logistic regression cost function in the Neural Network Model to improve the generalization capability of the model. At the same time, making the model architecture better by hyper-parameter tuning is essential. This work caters to the classification of Lithofacies using Well Log Data like density log, neutron porosity log and gamma ray log.