Sandia Labs FY22 Laboratory Directed Research & Development Annual Report

PREDICTING INDIVIDUAL DIFFERENCES IN COGNITION USING ADVANCED STATISTICS. The interdisciplinary research in the MIDAS:

Additionally, the outputs of the statistical methods show promise as a principled approach to quickly find regions within the EEG data where individual differences lie, thereby supporting cognitive science analysis and informing ML models. This work laid methodological groundwork for applying the large body of cognitive science literature on individual differences to high-consequence mission applications. An invited talk, “The Efficacy of Different Tasks for Modeling Individual Differences in Bilingual Language Proficiency,” was given on the project at the 62 nd Annual Meeting of the Psychonomic Society. (PI: Kyra Wisniewski)

Modeling Individual Differences using Advanced Statistics project explored novel methods for extracting relevant information from EEG data to characterize individual differences in cognitive processing. By using cognitive science expertise to interpret results and inform algorithm development, the LDRD team developed a generalizable and interpretable ML method to accurately predict individual differences in cognition. The output of the ML revealed surprising features of the EEG data that, when interpreted by the cognitive science experts, provided novel insights to the underlying cognitive task.

Sandia researchers wore caps like this one outfitted with EEG sensors while participating in an experiment that measures brain activity.

27

LABORATORY DIRECTED RESEARCH & DEVELOPMENT