Computer Vision Meetup: Hyperparameter Scheduling

Nearly all state-of-the-art results on computer vision benchmarks rely upon curated hyperparameter schedules. Though hyperparameter tuning may at times seem like a dark art, extensive empirical analysis of the topic has revealed countless numbers of best practices that are of incredible use to practitioners. In this talk, Cameron will overview these findings with an emphasis on practical applications, aiming to provide the listener with a better understanding of how to properly approach the tuning of hyperparameters.

Cameron Wolfe is a PhD student in Computer Science at Rice University in Houston, TX and a research scientist at Alegion, a software startup based in Austin, TX.

Read a summary of this presentation in the recap post:

Join the Computer Vision Meetup friendliest to your timezone:

Recorded on Jan 12, 2023 at the virtual Computer Vision Meetup.

#computervision #machinelearning #datascience #ai