Mixed state entanglement classification using artificial neural networks

Reliable methods for the classification and quantification of quantum entanglement are fundamental to understanding its exploitation in technologies. One such method, known as Separable Neural Network Quantum States (SNNS), employs a neural network inspired parameterisation states whose properties explicitly programmable. Combined with generative machine learning methods, this ansatz allows study very specific forms which can be used infer/measure target states. In work, we extend use SNNS mixed, multipartite states, providing versatile efficient tool investigation intricately entangled systems. We illustrate effectiveness our method through number examples, computation novel tripartite measures, approximation ultimate upper bounds qudit channel capacities.