Researchers hypothesize that a powerful type of AI model known as a transformer could be implemented in the brain through networks of neuron and astrocyte cells. The work could offer insights into how the brain works and help scientists understand why transformers are so effective at machine-learning tasks. Credit: MIT News with figures from iStockoffers insights into the potential role of astrocytes in the human brain.
, the researchers explored the role astrocytes play in the brain from a computational perspective, and crafted a mathematical model that shows how they could be used, along with neurons, to build a biologically plausible transformer. For self-attention to work, the transformer must keep all the words ready in some form of memory, Krotov explains, but this didn’t seem biologically possible due to the way neurons communicate.
The astrocyte collects some neurotransmitters that flow through the synaptic junction. At some point, the astrocyte can signal back to the neurons. Because astrocytes operate on a much longer time scale than neurons — they create signals by slowly elevating their calcium response and then decreasing it — these cells can hold and integrate information communicated to them from neurons. In this way, astrocytes can form a type of memory buffer, Krotov says.
“Sometimes, we found that certain things we wanted to be true couldn’t be plausibly implemented. So, we had to think of workarounds. There are some things in the paper that are very careful approximations of the transformer architecture to be able to match it in a biologically plausible way,” Kozachkov says.
Source: Education Headlines (educationheadlines.net)
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
Source: ScienceDaily - 🏆 452. / 53 Read more »
Source: SciTechDaily1 - 🏆 84. / 68 Read more »
Source: ComicBook - 🏆 65. / 68 Read more »
Source: SciTechDaily1 - 🏆 84. / 68 Read more »
Source: ScienceDaily - 🏆 452. / 53 Read more »
Source: CNN - 🏆 4. / 95 Read more »