Unsupervised Neural-Symbolic Integration
This addresses the gap in neural-symbolic integration for unsupervised learning, potentially enhancing interpretability and reasoning in domains like bioinformatics and relational data.
The paper tackles the problem of integrating symbolic knowledge into unsupervised neural networks, demonstrating the approach with propositional logic for DNA promoter prediction and first-order logic for family relationship understanding.
Symbolic has been long considered as a language of human intelligence while neural networks have advantages of robust computation and dealing with noisy data. The integration of neural-symbolic can offer better learning and reasoning while providing a means for interpretability through the representation of symbolic knowledge. Although previous works focus intensively on supervised feedforward neural networks, little has been done for the unsupervised counterparts. In this paper we show how to integrate symbolic knowledge into unsupervised neural networks. We exemplify our approach with knowledge in different forms, including propositional logic for DNA promoter prediction and first-order logic for understanding family relationship.