Artificial neural network have been successfully employed for providing efficient solutions for decision making problems and gained increased significance for their use in computer integrated manufacturing environment as effective tools for improving productivity and decision quality. The function of process planning in machining operations is a prominent one for neural network applications since it has direct impact on overall manufacturing productivity. This paper presents analysis and results of applying self-organizing neural networks to the selection of machining parameters of milling processes. The importance of this approach stems from the ability of neural nets to handle vague or ill-structured problems and the inherent capability of generalizing solutions to unseen problems. Furthermore, self-organizing neural networks do not require full knowledge of `output` data needed during the training phase; only a small portion of the data is needed for model calibiration. Simulations using ART1 neural model were applied to the selection of the tool material type and tool entry strategy, and the results demonstrated a high potential for the development of neural network modules for practical applications.