Is Artificial Intelligence Permanently Inscrutable? - Issue 40: Learning - Nautilus

As a research scientist at IBM, Malioutov spends part of his time building machine learning systems that solve difficult problems faced by IBM's corporate clients. The team tried several different methods, including various kinds of neural networks, as well as software-generated decision trees that produced clear, human-readable rules. It was hospital policy to send asthma sufferers with pneumonia to intensive care, and this policy worked so well that asthma sufferers almost never developed severe complications. He and other computer scientists are importing techniques from biological research that peer inside networks after the fashion of neuroscientists peering into brains: probing individual components, cataloguing how their internals respond to small changes in inputs, and even removing pieces to see how others compensate.