Compositional Connectionism in Cognitive Science:
Papers from the AAAI Fall Symposium
Simon D. Levy and Ross Gayler, Cochairs
Compositionality (the ability to combine constituents recursively) is generally taken to be essential to the open-ended productivity of perception, cognition, language and other human capabilities aspired to by AI. Ultimately, these capabilities are implemented by the neural networks of the brain, yet connectionist models have had difficulties with compositionality. This symposium will bring together connectionist and non-connectionist researchers to discuss and debate compositionality and connectionism. The aim of this symposium was to expose connectionist researchers to the broadest possible range of conceptions of composition—including those conceptions that pose the greatest challenge for connectionism—while simultaneously alerting other AI and cognitive science researchers to the range of possibilities for connectionist implementation of composition. Submissions from both proponents and critics of connectionist representations were encouraged, so long as the work described focuses on compositionality in the context of AI or cognitive science.