I am a Machine Learning Engineer at Adobe. My previous academic research broadly focused on how people learn and reason with concepts and categories, and how this knowledge is structured for useful inference. In particular, my work explores how interactions between inference and representation guide reasoning to enable efficient search and retrieval from semantic memory; to infer the appropriate level of generalization of meaning from few examples; and to help determine what makes something a good or bad member of a category.My work combines approaches from machine learning and cognitive science, including Bayesian statistics, graph theory, and information theory. I utilize large-scale behavioral experiments and datasets for evaluation. Sometimes I use methods from AI/ML to evaluate cognitive models and theories, and sometimes I use methods from cognitive science to improve the correspondence between AI/ML and cognitive models of generalization, and semantic representation.I completed my PhD at UC Berkeley in Tom Griffiths' Computational Cognitive Science Lab, and postdocs at the Center for Adaptive Rationality in the Max Planck Institute for Human Development, and at the Complex Human Data Hub in the University of Melbourne.Examples of my previous research: (1) transforming deep neural network representations to better capture human semantic representations, (2) developing both perceptual and conceptual models that learn appropriate generalization of label from few examples, and (3) determining what makes something a good or bad exemplar of a category.