AI Explains Brain Responses to Language

Microsoft Research, along with UC Berkeley, UCSF, and Columbia University, has introduced generative causal testing (GCT) to enhance the interpretability of AI models predicting brain responses to language. GCT distills these models into simple explanations of what brain regions respond to, and tests these explanations by generating stories that activate specific brain areas. This method has confirmed known brain selectivities and uncovered new prefrontal micro-regions. The research, published in Nature Neuroscience, suggests a new approach to understanding brain functions, bridging the gap between predictive models and scientific theories.