Recently a lot of work has been done in connection to using AI in the search for extraterestrial life, the SETI project.
Could the same methodology be used by the military, in order to detect submarines hiding in the world's oceans ? Basically the training data sets will have different characteristics, and the definition of what "relevant signals " are will change, but in principle the fundamental problem is the same, finding relevant signals in an "ocean of noise ". Is this assessment correct ? Is this avenue of research currently being considered already by the military ? You only need to answer the second question if the answer to the first is yes.
