Computer aided process planning (CAPP) is an effective way to integrate computer aided design and manufacturing (CAD/CAM). There are two key issues with the integration: design input in a feature-based model and acquisition and representation of process knowledge especially empirical knowledge. This paper presents a state of the art review of research in computer integrated manufacturing using neural network techniques. Neural network-based methods can eliminate some drawbacks of the conventional approaches, and therefore have attracted research attention particularly in recent years. The four main issues related to the neural network-based techniques, namely the topology of the neural network, input representation, the training method and the output format are discussed with the current systems. The outcomes of research using neural network techniques are studied, and the limitations and future work are outlined.