Osso VR - Surgery Training Platform

The team behind Osso VR, the VR surgical training platform, says that the software is now in use by more than 1,000 surgeons a month around the globe. The platform, which was created to provide surgeons with an immersive, repeatable environment to safely practice their craft, is now used by more than 20 teaching hospitals and eight top medical device companies across 11 countries. 

Besides offering risk-free practice sessions and performance analytics, the platform also helps bridge distances by letting surgeons train and be instructed on how to use new equipment without having to physically travel to conferences or location-based training sessions. Moreover, it can be done in a virtual environment one-on-one or in a group setting.

More information:

https://www.roadtovr.com/osso-vr-training-surgeons/

AI Beats Human Poker Champions

Carnegie Mellon University in collaboration with Facebook developed an AI application called Pluribus that reliably beat five professional poker players in the same game, or one pro pitted against five independent copies of itself. It’s a major leap forward in capability for the machines, and amazingly is also far more efficient than previous agents, as well. One-on-one poker is a weird game, but the zero-sum nature of it makes it susceptible to certain strategies in which a computer able to calculate out far enough can put itself at an advantage. But add four more players into the mix and things get real complex, real fast. With six players, the possibilities for hands, bets and possible outcomes are so numerous that it is effectively impossible to account for all of them, especially in a minute or less. It’d be like trying to exhaustively document every grain of sand on a beach between waves. Yet over 10,000 hands played with champions, Pluribus managed to win money at a steady rate, exposing no weaknesses or habits that its opponents could take advantage of. The secret is consistent randomness.

Pluribus was trained, like many game-playing AI agents these days, not by studying how humans play but by playing against itself. The training program used something called Monte Carlo counterfactual regret minimization. Sounds like when you have whiskey for breakfast after losing your shirt at the casino, and in a way it is machine learning-style. Regret minimization just means that when the system would finish a hand, it would then play that hand out again in different ways, exploring what might have happened had it checked here instead of raised, folded instead of called and so on. A Monte Carlo tree is a way of organizing and evaluating lots of possibilities, akin to climbing a tree of them branch by branch and noting the quality of each leaf you find, then picking the best one once you think you’ve climbed enough. If you do it ahead of time (this is done in chess, for instance) you’re looking for the best move to choose from. But if you combine it with the regret function, you’re looking through a catalog of possible ways the game could have gone and observing which would have had the best outcome.

More information:

https://techcrunch.com/2019/07/11/ai-smokes-5-poker-champs-at-a-time-in-no-limit-holdem-with-ruthless-consistency/

AI Predicts Better Severe Weather

Now, there is a computer model that can help forecasters recognize potential severe storms more quickly and accurately, thanks to a team of researchers at Penn State, AccuWeather, Inc., and the University of Almería in Spain. They have developed a framework based on machine learning linear classifiers (a kind of artificial intelligence) that detects rotational movements in clouds from satellite images that might have otherwise gone unnoticed. This AI solution ran on the Bridges supercomputer at the Pittsburgh Supercomputing Center. The very best forecasting incorporates as much data as possible. There's so much to take in, as the atmosphere is infinitely complex. By using the models and the data we have a snapshot of the most complete look of the atmosphere. 

In their study, the researchers analyzed more than 50,000 historical U.S. weather satellite images. In them, experts identified and labeled the shape and motion of ‘comma-shaped’ clouds. These cloud patterns are strongly associated with cyclone formations, which can lead to severe weather events including hail, thunderstorms, high winds and blizzards. Then, using computer vision and machine learning techniques, the researchers taught computers to automatically recognize and detect comma-shaped clouds in satellite images. The computers can then assist experts by pointing out in real time where, in an ocean of data, could they focus their attention in order to detect the onset of severe weather.

More information:

https://www.sciencedaily.com/releases/2019/07/190702160115.htm

Machine Enhanced Humans

Researchers have conquered the monumental task of manufacturing scalable nanoprobe arrays small enough to record the inner workings of human cardiac cells and primary neurons. The ability to read electrical activities from cells is the foundation of many biomedical procedures, such as brain activity mapping and neural prosthetics. Developing new tools for intracellular electrophysiology  that push the limits of what is physically possible (spatiotemporal resolution) while reducing invasiveness could provide a deeper understanding of electrogenic cells and their networks in tissues, as well as new directions for human-machine interfaces.

Ultra-small, flexible, nanowire probes could be a very powerful tool as they can measure intracellular signals with amplitudes comparable with those measured with patch clamp techniques; with the advantage of the device being scalable, it causes less discomfort and no fatal damage to the cell (cytosol dilation). Through this work, we found clear evidence for how both size and curvature affect device internalisation and intracellular recording signal. In the longer term, we see these probe developments adding to our capabilities that ultimately drive advanced high-resolution brain-machine interfaces and perhaps eventually bringing cyborgs to reality.

More information:

https://www.sciencedaily.com/releases/2019/07/190703121358.htm

Connect You to the Internet with a Brain Implant

Researchers believe that soon we will allow doctors to insert electrodes into our brains so we can communicate directly with computers and each other. Scientists have long known that the firing of our neurons is what allows us to move, feel, and think. But breaking the code by which neurons talk to each other and the rest of the body has long stood as one of neuroscience’s most daunting tasks. Using non-invasive electrodes that sit on the outside of the scalp makes the invention much less off-putting for patients, but it also imposes severe limitations. The voltage signals coming from brain cells may be muffled as they travel through the scalp to reach the sensors. 

In the next five to 10 years some form of brain-computer interface will be used to rehabilitate victims of strokes, spinal cord injuries, chronic pain, and other disorders. What you really want is to be able to listen to the brain and talk to the brain in a way that the brain cannot distinguish from the way it communicates internally, and we can’t do that right now. Where and when the breakthroughs will come from is unclear. After decades of research and progress, many of the same technological challenges remain daunting. Still, the progress in neuroscience and computer hardware and software makes the outcome inevitable.

More information:

https://www.technologyreview.com/s/609232/the-surgeon-who-wants-to-connect-you-to-the-internet-with-a-brain-implant/