utarlington
Latest
Robots can learn from their mistakes in real-time
Robots and other artificial intelligences can already learn from their mistakes, but they typically have to pause what they're doing to process what happened. They might not have to take a break in the future, though. Researchers have patented a technique, Integral Reinforcement Learning, that has devices continuously refining their actions based on each previous decision. If a machine doesn't already know the optimal way to handle a task, it can keep walking through the scenario (whether by predicting the outcome or actually trying) until it gets things right.
Biomask project could regrow burn victims' faces
We know it's cliche to say something sounds like science fiction, but this is seriously one of the more far out there concepts we've ever heard. Researchers from UT Arlington and Northwestern University are working with surgeons from the Brooke Army Medical Center on a project called Biomask. The idea is to skip surgery and have patients wear a mask, layered with sensors, actuators and medicine delivery tools for several months while their face slowly regenerates. The outside of the medical miracle would be a hard shell to protect the electronics and the injured person's healing face. Underneath, a second layer would monitor tissue growth, watch for infections and feed data back to doctors. An on board system would be able to dynamically alter the treatment, sending antibiotics or stem cells where they're needed. The team actually hope to turn this facial reconstruction mask into a reality by 2017, a goal that we'll diplomatically call optimistic. Full PR is after the break.