Artificial Neural Networks (ANN) are generally presented as systems of interconnected “neurons” which can compute values from inputs. It began to use at first in 1940s by Warren McCulloch and Walter Pitts (1943) by creating computational mode based on mathematics algorithms and was followed by Donald Hebb (1948) which created a hypothesis of learning based on the mechanism of neural plasticity. Farley and Wesley A. Clark (1954) first used computational machines . The Artificial Neural Network is built with a systematic step-by-step procedure to optimize a performance criterion or to follow some implicit internal constraint, which is commonly referred to as the learning rule . ANN have been used in the fields of concrete structures for nearly 25 years by many researchers: Tang et al. (2003), Oreta (2004), Fonseca et al. (2003), D. Maity and A. Saha (2004). These researchers basically set the structural parameters such as the material property, the boundary condition and the size of a structure as the input of the ANN model to predict the ability for the structure to resist the load . In most of these works, the neural networks have been trained by using back propagation algorithm. In this approach, the connection weights of neural networks are initially set to some random values. These values are then modified automatically according to the learning algorithm during the process of learning.