Learning Task-General Representations with Generative Neuro-Symbolic Modeling
share
A hallmark of human intelligence is the ability to interact directly with raw data and acquire rich, general-purpose conceptual representations. In machine learning, symbolic models can capture the compositional and causal knowledge that enables flexible generalization, but they struggle to learn from raw inputs, relying on strong abstractions and simplifying assumptions. Neural network models can learn directly from raw data, but they struggle to capture compositional and causal structure and typically must retrain to tackle new tasks. To help bridge this gap, we propose Generative Neuro-Symbolic (GNS) Modeling, a framework for learning task-general representations by combining the structure of symbolic models with the expressivity of neural networks. Concepts and conceptual background knowledge are represented as probabilistic programs with neural network sub-routines, maintaining explicit causal and compositional structure while capturing nonparametric relationships and learning directly from raw data. We apply GNS to the Omniglot challenge of learning simple visual concepts at a human level. We report competitive results on 4 unique tasks including one-shot classification, parsing, generating new exemplars, and generating new concepts. To our knowledge, this is the strongest neurally-grounded model to complete a diverse set of Omniglot tasks.
READ FULL TEXT
