In a scenario reminiscent of a sci-fi horror film, scientists have merged the biological and electronic worlds. The study, discussed in Nature Electronics, describes a “hybrid biocomputer” named Brainoware, which joins lab-grown human brain tissue with traditional circuits and AI. This system can recognize voices with 78 percent accuracy, and it may pave the way for silicon microchips connected with neurons.
Brainoware consists of brain organoids, which are clusters of human cells made into neuron-filled “mini-brains,” combined with regular electronic circuits. To create this system, researchers placed a single organoid on a plate containing thousands of electrodes to connect the brain to electric circuits. These circuits communicate with the brain through a pattern of electric pulses. The brain tissue learns and interacts with the technology, with a sensor detecting the mini-brain’s response and a trained machine-learning algorithm interpreting it.
The researchers trained Brainoware to recognize human voices using 240 recordings of eight people speaking, which were translated into electric signals for the organoid to process. The organic part reacted differently to each voice, generating a pattern of neural activity that the AI learned to understand, resulting in a 78 percent accuracy in identifying the voices.
The team regards this work as proof of concept rather than something with immediate practical applications. Despite past studies showing similar capabilities in two-dimensional neuron cell cultures, this is the first attempt at using a trained three-dimensional lump of human brain cells. This could lead to a future of biological computing, fueling superpowered AI based on the speed and efficiency of human brains.
Arti Ahluwalia, a biomedical engineer at Italy’s University of Pisa, believes this technology can shed more light on the human brain and help model and study neurological disorders like Alzheimer’s. The challenges for this unusual proto-cyborg technology include keeping the organoids alive and adapting them for more complex tasks, while striving for greater stability and reliability.