Title: Building Machine Learning Models like Open-Source Software
Speaker: Colin Raffel, UNC, HuggingFace
Date: February 8
Time: 3:30 PM - 4:20 PM
Pre-trained models have become a cornerstone of modern ML pipelines thanks to the fact that they can provide improved performance with less labeled data on downstream tasks. However, these models are typically created by a resource-rich research group that unilaterally decides how a given model should be built, trained, and released, after which point it is left as-is until a better pre-trained model comes along to completely supplant it. In this talk, I will present a vision for building machine learning models in the way that open-source software is developed - by a distributed community of contributors who iteratively build valuable artifacts through a mature set of tools including version control, continuous integration, merging, and more.
Colin Raffel is an Assistant Professor at UNC Chapel Hill and a Faculty Researcher at Hugging Face. His work aims to make it easy to get computers to do new things. Consequently, he works mainly on machine learning (enabling computers to learn from examples) and natural language processing (enabling computers to communicate in natural language). He received his Ph.D. from Columbia University in 2016 and spent five years as a research scientist at Google Brain.