On the Training Algorithms for Artificial Neural Network in Predicting the Shear Strength of Deep Beams

This study aims to predict the shear strength of reinforced concrete (RC) deep beams based on artificial neural network (ANN) using four training algorithms, namely, Levenberg–Marquardt (ANN-LM), quasi-Newton method (ANN-QN), conjugate gradient (ANN-CG), and descent (ANN-GD). A database containing 106 results RC beam tests is collected used investigate performance proposed algorithms. The ANN phase uses 70% data, randomly taken from dataset, whereas remaining 30% data are for algorithms’ evaluation process. structure consists an input layer with 9 neurons corresponding parameters, a hidden 10 neurons, output 1 neuron representing beams. models performed statistical criteria, including correlation coefficient (R), root mean square error (RMSE), absolute (MAE), percentage (MAPE). show that ANN-CG model has best prediction R = 0.992, RMSE 14.02, MAE 14.24, MAPE 6.84. this can accurately beams, promising useful alternative design solution structural engineers.