Computational Science Initiative Event

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.