Scientists have made a pocket-sized AI brain, thanks to the help of monkey neurons. Researchers using data from macaque monkeys were able to shrink an AI vision model to a tiny fraction of its original size. This achievement hints at how living brains are able to do so much with so little. The model, which mimics a part of the brain's visual system, started out using 60 million variables, but the team was able to compress it into a version that performed nearly as well using just 10,000 variables. This compact model also appears to work more like a living brain, which could help scientists study what goes wrong in diseases like Alzheimer's. If the AI model really does replicate strategies found in nature, it could help scientists understand the inner workings of human brains. Compact, biology-inspired models of the brain could also lead to more powerful and more humanlike artificial intelligence. The study is part of an effort to understand the human visual system, which takes in bits of light and transforms them into something we recognize. The specialized nature of these V4 neurons may help explain how human and other primate brains are able to make sense of what they see without relying on massive computing power. The findings also may have implications for artificial intelligence. For example, self-driving cars might be able to run on less powerful computers, while correctly distinguishing a pedestrian from an airborne plastic bag. However, AI systems need to do more than shrink in order to perform as well as a human brain. AI systems struggle with tasks like easily recognizing a friend's face in any setting and from many angles, even if that friend has acquired a suntan or is sporting a new haircut. This may be because current AI models are based on an understanding of the human brain from the 20th century, and since then, we learned a lot more about the brain. So maybe we should update the foundations of the artificial networks.
