DEEP ADAPTIVE SEMANTIC LOGIC (DASL): COMPILING DECLARATIVE KNOWLEDGE INTO DEEP NEURAL NETWORKS

Karan Sikka, Andrew Silberfarb, John Byrnes, Indranil Sur, Ed Chow, Ajay Divakaran, Richard Rohwer

Keywords: deep neural networks, first order logic, neuro-symbolic computing, knowledge, commonsense

Abstract:

We introduce Deep Adaptive Semantic Logic (DASL), a novel framework for automating the generation of deep neural networks that incorporates user-provided formal knowledge to improve learning from data. We provide formal semantics that demonstrate that our knowledge representation captures all of first order logic and that finite sampling from infinite domains converges to correct truth values. DASL’s representation improves on prior neuro-symbolic work by avoiding vanishing gradients, allowing deeper logical structure, and enabling richer interactions between the knowledge and learning components. We illustrate DASL through a toy problem in which we add structure to an image classification problem and demonstrate that knowledge of that structure
reduces data requirements by a factor of 1000. We apply DASL on a visual relationship detection task and demonstrate that the addition of commonsense knowledge improves performance by 10.7% in a data scarce setting.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

One-sentence Summary: DASL- a novel neuro-symbolic framework capturing full first order logic to improve learning with knowledge

Reviewed Version (pdf): https://openreview.net/references/pdf?id=ksrTbeEQEr