AI Made from Living Brain Cells

Scientists at Indiana University Bloomington have developed a biocomputing system using living brain cells for speech recognition.,The system, called "Brainoware," achieved 70-80% accuracy in recognising an individual's voice from a set of audio clips after two days of training.,This innovation could potentially address the high energy consumption and limitations of silicon chips in conventional AI.

Imagine a world where artificial intelligence (AI) is powered by living brain cells rather than silicon chips. Scientists at Indiana University Bloomington are turning this vision into reality with their groundbreaking biocomputing system, "Brainoware." This innovative technology uses balls of human brain cells linked to a computer to perform speech recognition tasks, potentially revolutionising the AI landscape in Asia and beyond.

Brain Organoids: The Mini-Brains Behind Brainoware

Brain organoids are lumps of nerve cells that form when stem cells are grown under specific conditions. "They are like mini-brains," says Feng Guo, a researcher at Indiana University Bloomington. It takes two to three months to grow these organoids, which are a few millimetres wide and contain up to 100 million nerve cells.

The organoids are placed on top of a microelectrode array, which sends electrical signals to the organoid and detects when nerve cells fire in response. This forms the basis of the Brainoware system.

Speech Recognition with Brainoware

In a remarkable feat, the Brainoware system was tasked with recognising an individual's voice from a set of 240 audio clips of eight people pronouncing Japanese vowel sounds. The clips were sent to the organoids as sequences of signals arranged in spatial patterns.

Initially, the organoids' responses had an accuracy of around 30-40%. However, after two days of training, their accuracy rose to an impressive 70-80%. Guo refers to this process as "adaptive learning."

Overcoming Conventional AI Challenges

Guo highlights two significant challenges with conventional AI: high energy consumption and the inherent limitations of silicon chips, such as their separation of information and processing. The Brainoware system aims to tackle these issues by harnessing the power of living nerve cells for biocomputing. This kind of innovation could impact everything from AI in call centres to advanced robotics, like those discussed in SoftBank's Big Bet.

The Future of Biocomputing and AI in Asia

The potential applications of biocomputing in AI are vast, and Asia is poised to be at the forefront of this technological revolution. With ongoing research and advancements, biocomputing systems like Brainoware could transform various industries, from healthcare to entertainment. For instance, the principles of structured governance seen in regions like North Asia might be crucial in regulating such advanced biotechnologies.

However, there are still hurdles to overcome. One major issue is that the organoids can only be maintained for one or two months. Guo and his team are working on extending this period to unlock the full potential of Brainoware. More detailed research on brain organoids and their applications can be found in scientific publications such as this one.

Comment and Share

What do you think about the potential of biocomputing systems like Brainoware in revolutionising AI? Share your thoughts below and don't forget to Subscribe to our newsletter for updates on AI and AGI developments in Asia.

YOUR TAKE

We cover the story. You tell us what it means on the ground.