DARPA Wants Artificial Intelligence To Explain Itself

The Pentagon wants to incorporate artificial intelligence into more systems but first needs to ensure its employees fully understand what drives AI, a new broad agency announcement suggests.  Potential applications for defense are endless—autonomous aerial and undersea war-fighting or surveillance, among others—but humans won’t make full use of AI until they trust it won’t fail, according to the Defense Advanced Research Projects Agency. A new DARPA effort aims to nurture communication between machines and humans by investing in AI that can explain itself as it works. An intelligence analyst who receives recommendations from algorithms about what to investigate further “needs to understand why the algorithm has recommended certain activity,” the BAA said. And the personnel overseeing a new autonomous system needs to know why it makes decisions so they “can decide how to use it in…


Link to Full Article: DARPA Wants Artificial Intelligence To Explain Itself