Unreasonable effectiveness of unsupervised learning in identifying Majorana topology
This provides a tool for identifying topology in Majorana nanowires, which is incremental as it builds on existing methods by integrating unsupervised learning.
The authors tackled the problem of identifying topological order in Majorana nanowires by combining unsupervised and supervised learning with an autoencoder, enabling distinction between topological and trivial phases and locating their crossover in parameter space using unlabeled data from disordered nanowires.
In unsupervised learning, the training data for deep learning does not come with any labels, thus forcing the algorithm to discover hidden patterns in the data for discerning useful information. This, in principle, could be a powerful tool in identifying topological order since topology does not always manifest in obvious physical ways (e.g., topological superconductivity) for its decisive confirmation. The problem, however, is that unsupervised learning is a difficult challenge, necessitating huge computing resources, which may not always work. In the current work, we combine unsupervised and supervised learning using an autoencoder to establish that unlabeled data in the Majorana splitting in realistic short disordered nanowires may enable not only a distinction between `topological' and `trivial', but also where their crossover happens in the relevant parameter space. This may be a useful tool in identifying topology in Majorana nanowires.