Zhejiang University Research Team Develops AI Model Inspired by Human Brain
A research team from Zhejiang University has proposed a novel approach to artificial intelligence (AI) that mimics the human brain's method of understanding the world. Published in Nature Communications, the study highlights the limitations of current AI models, which improve in recognizing specific objects as they scale up but struggle with abstract concepts. The team suggests using brain signals to guide AI models, making their classification methods more akin to human cognition. This approach aims to transfer 'human conceptual structures' to deep neural networks (DNNs), enhancing their ability to generalize and categorize new information. Experiments showed that models trained with brain signal data performed better in novel situations, indicating a potential shift from the 'bigger is better' paradigm to a more structured, brain-like model. 
