The ball of neurons, known as an organoid, created in Guo's lab is less than a nanometer wide. It was connected by an array of electrodes to a circuit board, where machine-learning algorithms decoded responses from the organoid.
After a brief training period, Brainoware was able to distinguish between the voices of eight subjects based on their varying pronunciation of vowels. The system achieved an accuracy rate of 78%.
Brainoware was also able to successfully predict a Henon map, a mathematical construct in the field of chaotic dynamics, with greater accuracy than an artificial network.
Incredible development in the area of biocomputing, and either someone has a great sense of 1950s retro humor to call it brain-o-ware, or they are horrible at coming up with names. All that matters is that the research is astounding.
