Fantastic Futures 2019 Conference

October 2, 2019
Catherine Nicole Coleman
Fantastic Futures logo

Stanford Libraries will host the 2nd International Conference on  AI for Libraries, Archives, and Museums over three days, December 4, 5 & 6, 2019. The first 'Fantastic Futures' conference, which took place in December 2018 at the National Library of Norway in Oslo, initiated a community-focused approach to addressing the challenges and possibilities for libraries, archives, and museums in the era of artificial intelligence. The Stanford conference will expand that charge, adding to the plenary gathering a full day of workshops and a half day 'unconference' shaped by the interests of those assembled.

Wednesday, December 4, will be a day of plenary sessions to introduce attendees to a range of topics in AI, from the concerns of algorithmic bias and data privacy to the exciting developments in transforming discovery and digital content curation (see the full program). The two keynote addresses reflect Stanford Library's position as an academic center in close proximity to Silicon Valley: Bryan Catanzaro, the Vice President of Applied Deep Learning at Nvidia, will speak to the important contribution he thinks libraries can make in AI. The second keynote speaker, Joanna Bryson, will speak to the ethics and regulation of AI. Currently a professor of computer science at the University of Bath, in 2020 Bryson will take up a new position as Professor of Ethics and Technology at The Hertie School of Governance, in Berlin. Later in the day, a conversation led by Ashley Jester with Rachel Thomas and Angele Christin will continue that thread with a dive into data privacy, algorithmic bias and the implications of using algorithmic predictions in public policy. 

A series of lightning talks will expose attendees to a wide range of applications of AI currently underway in libraries, archives, and museums. Elena Nieddu (Roma Tre University) will share In Codice Ratio's innovative approach to training models for automating transcription of documents from the Vatican Secret Archives. Peter Leonard (Yale) and Thomas Smits (National Library of the Netherlands) will demonstrate work with image-based materials (see Leonard's work on Neural Neighbors, Pix Plot, and Robots Reading Vogue). And Thomas Van Dijk  (University of Würzburg) will demonstrate techniques for automating extraction of historical map data.  A second moderated discussion, led by Vanessa Kam, will consider the implications of AI not only for how we access and analyze visual collections, but for how visual art is produced and studied.

Other lighting talks will focus on programmatic implementations of AI: Emmanuelle Bermès (National Library of France) will present Corpus, a project to provide the space and the tools for excavation and exploration of texts and data. We will learn about recent developments in the National Library of Norway's 'Nancy' project from Svein Arne Brygfjeld. Katie McDonough will share the first year's work of the five-year 'Living With Machines' collaboration between the Alan Turing Institute and the British Library. Many of the presenters will also be instructors for the Workshops day, Thursday, December 5. (See a description of the four workshop tracks here.)

One of the concerns voiced at the first Fantastic Futures workshop session was how to make use of these new technologies without in-house engineers and on limited budgets. In response to that, we have included a series of lighting talks on 'democratizing AI.' Rachel Thomas, co-founder of and Teemu Roos, creator of 'Elements of AI' will talk about approaches to increasing AI literacy—not just for engineers, but for everyone. And we will see a demonstration of recent work at MIT to develop an interactive visual platform to empower people without expertise in statistics or machine learning to build, analyze, and evaluate machine learning (ML) pipelines.

The AI Initiative at Stanford Libraries has been, from its inception, purpose-driven rather than technology-driven. The potential for the implementation of AI technologies to transform how we do our work requires that we bring everyone, in all roles across our institutions, into the conversation, the planning, and the design. In that spirit, Fantastic Futures 2019 encourages participation from administration, acquisition, archives, curation, cataloging, conservation, design, engineering, and any other area that might benefit from, or contribute to, technology change. We hope that this conference will be an opportunity to learn together, work together, and begin to build a LAM community of practice that will bring our content and subject expertise together with engineering talents to make the most of AI.