The use of carbon fiber reinforced composite materials is an accepted technology that is being used in practice to strengthen existing reinforced concrete (R/C) elements. An artificial neural network (ANN) model was developed using past experimental data on flexural failure of R/C beams strengthened by carbon FRP. The input parameters cover the carbon sheet properties, beam geometrical properties and reinforcement properties; the corresponding output is the ultimate load capacity. The ANN prediction and the measured experimental values are compared with load prediction of ACI440.2R-02 formulas. A sensitivity study of parameters that affect ultimate load of R/C beams strengthened by carbon FRP is carried out. It is concluded that ANN can predict, to a good degree of accuracy, the ultimate load capacity of R/C beams strengthened by carbon FRP and it is a viable tool to carry out parametric study of flexural behavior of R/C beams strengthened by carbon FRP.