top of page
Untitled design.jpg

ABOUT ME

Hello, world! I'm Nicole. I’m a PhD candidate at Yale University. My research examines how architectural constraints shape representational capacity in deep neural networks, and how this affects things like controllability and safety. To do this work, I combine mathematical analysis of model architectures with causal interventions on toy and trained systems.

 

Outside of research, I spend my time playing folk music, growing tomatoes, and enjoying the outdoors with my family. 

Selected Projects

1 / Architectural Constraints on Feature Emergence in Neural Audio Models

My dissertation project. The guiding question is: Do semantically meaningful musical features (e.g., pitch, melody, harmony) emerge as controllable internal variables in modern end-to-end audio models?

2 / Musicological Interpretability with Generative Transformers

A project with my lab group: We analyzed the embeddings of an autoregressive transformer as it trained on symbolic music data, to understand how music-grammatical roles emerge.

3 / Play A Song From the 'Jukebox'

Early interpretability experiments on deep generative audio models. 

bottom of page