Caleb Belth

[keɪləb bɛlθ] (he/him)

Welcome! I'm a PhD candidate at the University of Michigan, where my advisor is Danai Koutra.

My research interests fall in linguistics, computer science, and the study of mind. In particular, I study how principles of computational efficiency, such as memory limitations and avoidance of unnecessary change, influence the structure of language and allow children to more easily acquire it. I also research how contributions to such understanding can be used to improve the sustainability of natural language processing and its application beyond English.

My prior research has contributed methods for choosing unlinked pairs of nodes to investigate further with a link prediction method or experimental study, identifying subtle patterns in networks that are too infrequent to be discovered by frequency alone, and for discovering errors and missing information in incomplete knowledge graphs. Applications of this work include anomaly detection, suspicious behavior discovery, and city/urban planning, including current projects with the City of Detroit on transportation planning.

I am grateful to have been selected for 2020-2023 NSF GRF and NDSEG fellowships. I am currently funded by the NSF GRF.

Prior to Michigan, I received a B.Sc. in Computer Science from Purdue University, where I was fortunate to work with Jennifer Neville, Dan Goldwasser, and Daisuke Kihara.

Feel free to contact me at cbelth@umich.edu.
In case you are wondering, the name of this website ("quickshift") is a nod to my life-long love of road trips, driving, and cars in general.


Creative Content


Abiogenesis [link]

Somewhere in the Universe [link]

Goo [link]

The Cat (Part 1) [link]

Projection (1) [link]


A rock comedian. [image]
Philosophy, Consciousness


Cliff edge. [image]