The millions of digitized historic newspaper pages within Chronicling America, a joint initiative between the Library of Congress and the National Endowment for the Humanities, represent an incredibly rich resource for the American public. Historians, journalists, genealogists, students, and members of the American public explore the collection regularly via keyword search. But how do we navigate the abundant visual content? In this talk, I will present my project, Newspaper Navigator, created in collaboration with LC Labs, the National Digital Newspaper Program, and IT Design & Development at the Library of Congress, as well as Professor Daniel Weld at the University of Washington. In particular, I will discuss the two phases of Newspaper Navigator: extracting visual content from 16+ million pages in Chronicling America (resulting in the Newspaper Navigator dataset) and re-imagining how we search over the extracted visual content using the Newspaper Navigator search application. I will also discuss how this project can contribute to research in machine learning, human-computer interaction, and the digital humanities. I will conclude by contextualizing Newspaper Navigator within a large body of emerging work foregrounding machine learning within libraries and other cultural heritage institutions.