If you’re a scientist who wants to do something to help kids with cerebral palsy, your first strategy probably isn’t to launch an internet contest with freaky skeleton videos, but that is more or less what Łukasz Kidziński, PhD, did.
Of course, the videos themselves are not really the point. Instead, it’s what’s under the hood that matters — contestant-submitted machine learning algorithms that have figured out how to walk. Kidziński works in the lab of Scott Delp, PhD, a professor of bioengineering and mechanical engineering, who has spent years building highly accurate models of human muscles and bones. Ideally, those models could help doctors make better predictions about how people with cerebral palsy will walk after undergoing surgery to ease overly tense muscles. The problem is that currently the best models only deal with the actual mechanics of walking, not how people learn or relearn to walk.
Delp explains more in my Stanford News story:
‘Whereas we’ve gotten quite good at building computational models of muscles and joints and bones and how the whole system is connected – how the human machine is built – an open challenge is how your brain orchestrates and controls this complex dynamic system,’ Delp said.
Machine learning, a variety of artificial intelligence, has reached a point where it could be a useful tool for modeling of the brain’s movement control systems, Delp said, but for the most part its practitioners have been interested in self-driving cars, playing complex games like chess or serving up more effective online ads.
‘The time was right for a challenge like this,’ Delp said, in part because some in the machine learning community are looking for more meaningful problems to work on, and because bioengineers stand to gain from understanding more about machine learning.’
The final results will be presented at the 2017 Neural Information Processing Systems meeting in December.
Previously: Why become a doctor? “Fixing the brain” is not impossible and Seeing the beauty in disability
Image courtesy of Stanford Neuromuscular Biomechanics Lab