The conference

COCO's Memory Palace: Where Image and Poem Meet

Every supervised recognition problem in machine learning requires a algorithm's memory of data.  Every story or poem a human writes requires a human's memory of living in the world.  At the intersection of human and machine memory, new opportunities arise for creativity.  In this talk we'll see battling image recognizers remembering both the Parthenon and the crowded front of an American refrigerator; we'll walk thru a story generation graph visually; and we'll write poems using a photograph's colors and a word2vec maze.  The magical transformation common in all these AI toys is making the image textual and the textual visual.  The algorithms' memories will do all the hard work: we'll just invite them to guide us through the palace.

 

Learn more about

Lynn Cherny

Lynn Cherny is an Associate Professor of Data Science in Lyon, France.  She works on data visualization, text mining, and machine learning & AI.  Her artistic interests center on narrative and poetry generation, combining images and visuals in interactive forms that surprise and delight.  She has a Ph.D. in Linguistics, and has been a researcher at AT&T Labs and a user interface designer at companies including Adobe, TiVo, The Mathworks, Autodesk, and Solidworks.