Differentiable Probabilistic Logic Networks

TL;DR

This paper introduces a differentiable probabilistic logic network that enables learning and reasoning over tensor-based truth values, integrating symbolic logic with neural network training via backpropagation.

Contribution

It presents a novel differentiable framework for probabilistic logic that combines symbolic reasoning with subsymbolic learning using tensor operations.

Findings

Enables end-to-end training of logic-based reasoning systems

Supports hybrid symbolic and neural inference methods

Demonstrates potential for improved cognitive architectures

Abstract

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.