Summary: Researchers developed a new GPU-based machine learning algorithm to help predict the connectivity of networks within the brain. A new GPU-based machine learning algorithm developed by researchers at the Indian Institute of Science (IISc) can help scientists better understand and predict connectivity between different regions of the brain. The algorithm, called Regularized, Accelerated, Linear Fascicle Evaluation, or ReAl-LiFE, can rapidly analyse the enormous amounts of data generated from diffusion Magnetic Resonance Imaging (dMRI) scans of the human brain. Using ReAL-LiFE, the team was able to evaluate dMRI data over 150 times faster than existing state-of-the-art algorithms. "Tasks that previously took hours to days can be completed within seconds to minutes," says Devarajan Sridharan, Associate Professor at the Centre for Neuroscience (CNS), IISc, and corresponding author of the study published in the journal Nature Computational Science.

We focus on the problem of teaching a robot to solve tasks presented sequentially, i.e., in a continual learning scenario. The robot should be able to solve all tasks it has encountered, without forgetting past tasks. We provide preliminary work on applying Reinforcement Learning to such setting, on 2D navigation tasks for a 3 wheel omni-directional robot. Our approach takes advantage of state representation learning and policy distillation. Policies are trained using learned features as input, rather than raw observations, allowing better sample efficiency. Policy distillation is used to combine multiple policies into a single one that solves all encountered tasks.

Next time around, it will be one small step for a robot, one giant leap for software coders. For decades sci-fi movies have predicted that people will someday travel on enormous spaceships to distant stars. But in the age of robotic landers and explorers, the argument for sending people into space is becoming weaker. Not only is it highly risky, it's also astronomically expensive and galactically difficult to create the life support systems needed for interplanetary travel. It's much easier to send a robotic explorer that needs no oxygen or food, never goes to the bathroom and can hibernate for years while travelling to distant celestial bodies. And if that's not enough, NASA is actually working on a robotic astronaut.

Robots are helping to keep the lights on in China's Anhui province. The robots look remarkably like Disney's lovable "Wall-E." Don't let that fool you, though. The machines are hard at work. Humans tell the robots what to keep an eye on, but the inspector bots do their job on their own.

Yuuta Banda poses for a photo with OriHime, his robot avatar. When Yuuta Banda was just four years old, he suffered a car accident that left him paralyzed, connected to a respiratory machine, and confined to bed for life. But almost two decades later, he's been able to experience different places, and even find a job thanks to OriHime, his robot avatar. "At first I couldn't understand what was so great about OriHime, but I gradually learned through using it that [the robot] afforded people with a sense of presence," Banda told me in an email. "I felt a greater sense of satisfaction as I spoke with people in different places to me through the robot."