Creative Support Companions: Some Ideas

                                               Ken Forbus
                           Walter P. Murphy Professor of Computer Science and
                                        Professor of Education at
                                        Northwestern University
                                       forbus@northwestern.edu




                                                        Abstract
                       An exciting opportunity for AI is the development of intelligent assis-
                       tants that, working with people, enable them to do far more than they
                       can alone. What would that mean for creative activities? This talk
                       explores some ideas for using the Companion cognitive architecture to
                       create software collaborators that support creative work. Companions
                       include human-like analogical processing, facilities for natural language
                       and sketch understanding, and rich relational representations that cap-
                       ture aspects of human visual, spatial, and conceptual knowledge. For
                       supporting creative activities, this should enable them to (1) help sug-
                       gest and explore cross-domain analogies, (2) interact via natural modal-
                       ities, providing higher communication bandwidth and reducing friction
                       compared to software tools, and (3) adapt to their human partners over
                       time, building up a portfolio of joint work that can be drawn upon in
                       future efforts.




Copyright c by the paper’s authors. Copying permitted for private and academic purposes.
In: A.M. Olteteanu, Z. Falomir (eds.): Proceedings of ProSocrates 2017: Symposium on Problem-solving, Creativity and Spatial
Reasoning in Cognitive Systems, at Delmenhorst, Germany, July 2017, published at http://ceur-ws.org