Microsoft Research@MSFTResearch · XAI 摘要
研究人员引入了生成式因果测试，它将黑箱模型转化为清晰的假设，并在扫描仪中进行验证，揭示了大脑特定区域对语言的反应。
Researchers introduce generative causal testing， which translates black box models into clear hypotheses and verifies them in the scanner， revealing what specific brain regions respond to in language. https://msft.it/6011vUtRd