Differentiable Probabilistic Logic Networks
This work addresses the need for hybrid symbolic-subsymbolic AI systems, such as in cognitive architectures like OpenCog, though it appears incremental as it adapts an existing framework.
The paper tackles the problem of integrating probabilistic logic reasoning with gradient-based learning by introducing a differentiable version of Probabilistic Logic Networks, enabling learning of truth values and rule formulas through backpropagation.
Probabilistic logic reasoning is a central component of such cognitive architectures as OpenCog. However, as an integrative architecture, OpenCog facilitates cognitive synergy via hybridization of different inference methods. In this paper, we introduce a differentiable version of Probabilistic Logic networks, which rules operate over tensor truth values in such a way that a chain of reasoning steps constructs a computation graph over tensors that accepts truth values of premises from the knowledge base as input and produces truth values of conclusions as output. This allows for both learning truth values of premises and formulas for rules (specified in a form with trainable weights) by backpropagation combining subsymbolic optimization and symbolic reasoning.