Machining conditions are optimized to minimize the production cost in conventional manufacturing. In specialized manufacturing applications, such as micro machining and mold making, achievement of specific goals may be the primary objective. The Genetically Optimized Neural Network System (GONNS) is proposed for the selection of optimal cutting conditions from the experimental data when analytical or empirical mathematical models are not available. GONNS uses Backpropagation (BP) type neural networks (NN) to represent the input and output relations of the considered system. Genetic Algorithm (GA) obtains the optimal operational condition by using the NNs. In this study, multiple NNs represented the relationship between the cutting conditions and machining-related variables. Performance of the GONNS was tested in two case studies. Optimal operating conditions were found in the first case study to keep the cutting forces in the desired range, while a merit criterion (metal removal rate) was maximized in micro-end-milling. Optimal operating conditions were calculated in the second case study to obtain the best possible compromise between the roughness of machined mold surfaces and the duration of finishing cut. To train the NNs, 81 mold parts were machined at different cutting conditions and inspected. (c) 2005 Elsevier Ltd. All rights reserved.