The determination of cutting forces through experimental methods is prevalent as there exist no general mathematical models for the prediction of cutting forces with respect to machining and material parameters. However, undertaking such experiments for measuring such forces consistently is expensive and time-consuming. In particular, when machining composite materials, obtaining specimens with the required specifications can be extremely difficult. In the work reported here, a multi-layered perception feed forward artificial neural network has been developed to evaluate and compare the cutting forces developed during the machining of glass/epoxy, graphite/epoxy and kevlar/epoxy composites (Ramkumar et al, 2004). The fibre orientation, composition and the depth of cut undertaken were chosen as input parameters for this purpose. The cutting force values evaluated using finite element methods were used for training the artificial neural network. The artificial neural network outputs are compared with the desired output values and provided maximum error reduction. Finally, the comparison of the neural network output results with the results obtained from experiments has shown an acceptable level of convergence.