Data Ethics • Deep Learning • Perceptual Hashing • Convolutional Neural Networks • Semantic Segmentation • International Image Interoperability Framework • Neural Style Transfer • Data Science • Generative Adversarial Networks • Visualization • Variational Autoencoders • Manifold Learning • Transfer Learning • Computer-Assisted Curation • Computer Vision • Automated Captioning • Dimensionality Reduction • Culturally-Sensitive Data

Overview

The mass digitization of visual collections, on the order of hundreds of thousands or millions of images, creates new challenges for curators and researchers alike. Simultaneously, the rapid pace of industry innovation in deep learning (from guiding self-driving cars to captioning smartphone images) demands the attention of library, museum, and academic professionals.

Existing practices of cataloging and description can be augmented by recent advancements in machine vision, and human expertise can likewise guide the development of future algorithms for the humanities and sciences alike. To showcase work that’s underway and explore potential collaborations, the Yale-Smithsonian Partnership held a one-day symposium on the topic of machine learning for cultural heritage and natural science collections. The event brought together scholars and curators from both institutions for conversations, demonstrations, and future partnerships.

Keynote Speakers

• Rebecca Dikow (Data Science Lab, Smithsonian Institution)
• Holly Rushmeier (Computer Science, Yale)

Logistics

• Date: April 26, 2019
• Time: 10:00 a.m. – 4:00 p.m.
• Location: Franke Family Digital Humanities Laboratory, Sterling Memorial Library, 120 High Street, New Haven, CT

Schedule