Scientists Integrate Human Brain Cells into Computing Systems for Advanced AI Tasks
According to Decrypt, researchers at Indiana University Bloomington have developed a system called 'Brainoware' that integrates living human brain cells into computing systems. The system uses human brain organoids, artificially grown masses of cells or tissue that resemble an organ, to complete advanced AI tasks. Currently mounted on a high-density multielectrode array, these organoids are quite primitive but could pave the way for biocomputers that can execute the same tasks as computers with minimal energy consumption.
The research paper published in Nature Electronics states that a human brain typically expends about 20 watts, while current AI hardware consumes about 8 million watts to drive a comparative artificial neural network (ANN). Brainoware could provide additional insights for AI computing as brain organoids can provide biological neural networks (BNNs) with complexity, connectivity, neuroplasticity, and neurogenesis, as well as low energy consumption and fast learning. The system's practical potential was demonstrated through tasks like speech recognition, where it distinguished individual speakers' voices with increasing accuracy after training. However, the organoids could only identify a speaker, not understand the speech, indicating that there is still a long way to go before the technology achieves practical use in medicine or engineering.
Disclaimer: Includes thrid-party opinions. No financial advice. May include sponsored content. See T&Cs.