SLDR-DL: A Framework for SLD-Resolution with Deep Learning
This work addresses the challenge of efficient automated reasoning for AI systems, though it appears incremental as it builds on existing SLD-resolution and deep learning methods.
The paper tackles the problem of automating logical reasoning by introducing SLDR-DL, a framework that uses deep learning to guide SLD-resolution processes, enabling neural networks to learn from past successful resolutions and apply this knowledge to new reasoning tasks.
This paper introduces an SLD-resolution technique based on deep learning. This technique enables neural networks to learn from old and successful resolution processes and to use learnt experiences to guide new resolution processes. An implementation of this technique is named SLDR-DL. It includes a Prolog library of deep feedforward neural networks and some essential functions of resolution. In the SLDR-DL framework, users can define logical rules in the form of definite clauses and teach neural networks to use the rules in reasoning processes.