Generating new concepts with hybrid neuro-symbolic models
This work addresses the challenge of concept generation in cognitive science, offering an incremental improvement by combining existing traditions for better performance on visual concepts.
The paper tackles the problem of generating novel structured concepts by synthesizing symbolic and neural approaches, resulting in a hybrid neuro-symbolic model that outperforms generic neural models in likelihood and generalization on handwritten character data.
Human conceptual knowledge supports the ability to generate novel yet highly structured concepts, and the form of this conceptual knowledge is of great interest to cognitive scientists. One tradition has emphasized structured knowledge, viewing concepts as embedded in intuitive theories or organized in complex symbolic knowledge structures. A second tradition has emphasized statistical knowledge, viewing conceptual knowledge as an emerging from the rich correlational structure captured by training neural networks and other statistical models. In this paper, we explore a synthesis of these two traditions through a novel neuro-symbolic model for generating new concepts. Using simple visual concepts as a testbed, we bring together neural networks and symbolic probabilistic programs to learn a generative model of novel handwritten characters. Two alternative models are explored with more generic neural network architectures. We compare each of these three models for their likelihoods on held-out character classes and for the quality of their productions, finding that our hybrid model learns the most convincing representation and generalizes further from the training observations.