Garrison Weeks Cottrell

Garrison W. Cottrell is an American cognitive scientist and computer scientist who serves as a Professor of Computer Science and Engineering at the University of California, San Diego (UC San Diego). In 2017, he was named a Fellow of the Cognitive Science Society for his contributions to the field.

Education and career

Cottrell obtained his bachelor's degrees in mathematics and sociology as well as an M.A.T. in mathematics education from Cornell University. He then earned an M.S. and a Ph.D. in computer science at the University of Rochester, where he studied with James F. Allen. From 2006 onward, he served as founding director and principal investigator of the Temporal Dynamics of Learning Center (TDLC), a multi-institutional research initiative funded as one of the NSF’s Science of Learning Centers. Beyond face perception, his group has contributed to saliency-based vision models, neural network approaches for time-series prediction, and computational studies of reading and language comprehension.

Selected publications

Dollár, P., Rabaud, V., Cottrell, G., & Belongie, S. (2005). “Behavior recognition via sparse spatio-temporal features.” In 2005 IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance (pp. 65–72). IEEE.

Zhang, L., Tong, M.H., Marks, T.K., Shan, H., & Cottrell, G.W. (2008). “SUN: A Bayesian Framework for Saliency Using Natural Statistics.” Journal of Vision, 8(7), 32.

Qin, Y., Song, D., Chen, H., Cheng, W., Jiang, G., & Cottrell, G. (2017). “A Dual-Stage Attention-based Recurrent Neural Network for Time Series Prediction.” arXiv preprint arXiv:1704.02971.

Valentin, D., Abdi, H., O’Toole, A.J., & Cottrell, G.W. (1994). “Connectionist Models of Face Processing: A Survey.” Pattern Recognition, 27(9), 1209–1230.

Honors and awards

2017 – Fellow, Cognitive Science Society