Learning how to classify and detect properties of quantum systems is one of the leading challenges in improving our understanding of quantum entanglement. The tools of machine learning are increasingly useful in the task of efficiently classifying quantum states. The knowledge required for quantum machine learning is two-fold: it includes understanding how to represent quantum states along with the theory behind them, and also knowing how to apply and feed these into a machine learning algorithm. One of the most important theories in this task is Bell’s Inequalities. Since entanglement is necessary to violate Bell’s Inequalities, this mathematical relationship can be used as an entanglement detector. There has been a lot of progress in this field by using different machine learning architectures such as restricted artificial neural networks (ANN). This project will focus on implementing and improving the ANN model published by Ma and Yung in Nature. The results of the ANN model are replicated which show that accuracy increases when the points near the boundary of entangled and separable are removed. A random forest classifier is also tested with this data with less accuracy than an ANN model. The third test to manipulate the labels of the data yielded unsuccessful accuracy but provided insight into the relationship between eigenvalue and entanglement.