As machining is considered a very complex metal removal process with various nonlinear and multivariate problems, an automatic control system is essentially required to monitor the process, with the help of sensors, to ensure optimal parametric/operating conditions. Thus, the automated system should have a model that ensures appropriate decision-making on machining. This chapter is an overview on intelligent machining. The application of computational approaches and optimization methods, such as neural networks in modeling, fuzzy-set-based modeling, hybrid neuro-fuzzy modeling, finite element method, genetic algorithm, etc., for the development of intelligent machining systems like soft computing techniques are described in this chapter. Designing of experimental techniques for prediction models and optimization of responses in the machining process are also presented in brief. The selection of appropriate machining parameters is necessary for the improvement of product quality and productivity and the reduction of manufacturing cost in machining/manufacturing industries. This chapter also provides several single- and multi-criteria decision-making optimization techniques to obtain the desired cutting parameters for conventional and nonconventional machining processes. The findings are presented with due emphasis on the machining of nanocomposites.