In Additive Manufacturing (AM), recent developments in in-situ monitoring and process control allow the collection of large amounts of emissions data during the build and modification process of the parts being manufactured. This data then can be used as source to further construct 2D and 3D representations of the printed parts. However, the inspection, labeling and analysis as well as the characterisation of this data still remains a manual process. The aim of this research is to determine if and how Machine Learning techniques can automatically inspect and annotate this generated data, thereby reducing manual workload and associated costs. More specifically, this work will look at two scenarios: firstly, using convolutional neural networks (CNNs) to inspect and classify the data collected by in-situ monitoring and secondly, applying Active Learning and Semi-supervised learning to accelerate the data labeling process while continuously gaining understanding about the manufactured object from the data generated during the AM process. Ultimately this work could be used to help with decisions made by an AM operator during the AM process allowing modification of the output during the actual manufacture process