Deep Learning Machine Predicts Human Activity

The setting is a doctor’s office in the future. Rather than gathering impressions of a patient’s lifestyle via inquiry, the doctor collects a piece of wearable technology, on which the patient may record caloric intake and exercise rates. In this future, guesswork may no longer be required from a doctor during a check-up. “It would still require a lot of work to get there, but that’s kind of the dream in the future,” says Daniel Castro, a PhD computer science candidate at Georgia Institute of Technology, in an interview with R&D Magazine. Castro, along with colleagues at the institute’s School of Interactive Computing and the Institute for Robotics and Intelligent Machines, developed a model that allows a computer to predict—with over 83% accuracy—the activities a human engages in during the…


Link to Full Article: Deep Learning Machine Predicts Human Activity