A goal-driven neural propositional interpreter.
This work presents ARQ-PROP-II, the propositional version of a neural engine for finding proofs by refutation using the Resolution Principle. This neural architecture does not require special arrangements or modules to do forward or backward reasoning, being driven by the goal posed to it. ARQ-PROP-II is capable of integrated monotonic reasoning with complete and incomplete knowledge. The neural mechanism presented herein is the first to our knowledge that does not require that the knowledge base be either pre-encoded or learnt.
Goals↗