On Data-Driven Creativity
Creativity is defined to be the generation of an idea or artifact judged to be novel and also to be appropriate, useful, or valuable by a knowledgeable social group, and is oft-said to be the pinnacle of intelligence. Data-driven computational systems of varying designs, which produce creative artifacts in several domains, are now being demonstrated and deployed. I discuss our experiences in building such systems in domains including culinary, experiential learning activities for students, materials discovery, and music, and the general lessons we learned. The need for interpretable hierarchical concept learning is especially emphasized.
To engineering systems theorists, this zoo of possibilities also raises the natural question: are there fundamental limits to creativity? We present a general model of creative domains with combinatorial artifacts constructed from components and study fundamental tradeoffs between quality and novelty. Novelty is measured using the Bayesian surprise functional and quality is measured using concepts from within the domain. Information-theoretic limit theorems establish that the ease of creativity is determined by the maturity of the creative domain, governed by the ratio in the sizes of the known inspiration set and the full domain of possibilities. In separating generation and selection in creativity, the use of concomitants of order statistics to analyze performance emerges.
Lav Varshney is an assistant professor in the Department of Electrical and Computer Engineering and the Department of Computer Science (by courtesy), a research assistant professor in the Coordinated Science Laboratory, and a research affiliate in the Beckman Institute and in the Neuroscience Program, all at the University of Illinois at Urbana-Champaign. He is also leading curriculum initiatives for the new B.S. degree in Innovation, Leadership, and Engineering Entrepreneurship in the College of Engineering.
He received the B.S. degree (magna cum laude) in electrical and computer engineering with honors from Cornell University in 2004. He received the S.M., E.E., and Ph.D. degrees, all in electrical engineering and computer science, from the Massachusetts Institute of Technology, in 2006, 2008, and 2010, where his theses received the E. A. Guillemin Thesis Award and the J.-A. Kong Award Honorable Mention. He was a research staff member at the IBM Thomas J. Watson Research Center from 2010 until 2013, where he conceptualized the Chef Watson computational creativity system for novel and flavorful culinary recipes, and led its design and development. His research interests include information and coding theory; data science; limits of nanoscale, social, and neural computing; human decision making and collective intelligence; and creativity.
Dr. Varshney is a founding member of the IEEE Special Interest Group on Big Data in Signal Processing and serves on the Shannon Centenary Committee of the IEEE Information Theory Society. He also serves on the advisory board of the AI XPRIZE and on the NAS Science & Entertainment Exchange. He received the IBM Faculty Award in 2014 and was a finalist for the Bell Labs Prize in 2014 and 2016. He and his students have won several best paper awards, including a 2015 Data for Good Exchange Paper Award. His work appears in the anthology, The Best Writing on Mathematics 2014.