NASA, Industry Exploring Expanded Machine Learning For Future Spacecraft Written 24 August 2018

SPACE reports that NASA and industry researchers are “beginning to consider the use of machine learning and are looking into sharing training data sets” for future space missions. The use of deep learning technology to train computers to “recognize patterns based on training data” has been considered “too risky to use much for spacecraft decision-making,” but this “may change as missions grow more complicated and the cost of launching small spacecraft decreases.” According to MathWorks Space Segment Manager Ossi Saarela, for deep space missions, “the amount of precision you need for navigation is pretty spectacular, when you think about it, considering how far away those objects are and how small they can be.” Saarela expects the “proofs of concept to come from either startups or projects that are lower-cost, projects that are willing to tolerate higher risk.” 
More Info (SPACE)