Differentiable Production Systems

Production systems have had a remarkable influence on the history of artificial intelligence, though have fallen out of favour in recent years. We propose to take this classical computational mechanism, which have recently been central to efforts to model the flexibility of human behaviour, and modernize it to take advantage of recent advances in deep learning research. In particular, we propose a framework for constructing differentiable computation graphs that combines the strengths of both of these paradigms, namely the flexibility of behaviour of the former and trainability of the latter. Furthermore, we identify an ensemble of tasks that provide significant perceptual, computational and flexibility challenges, and propose to use our framework to train a single model capable of solving any of them without modification.

Authors

• Eric Crawford

Keywords

No keywords are indexed for this paper.