Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
arXiv:2003.07344
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 neural-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 . We then evaluate DASL on a visual relationship detection task and demonstrate that the addition of commonsense knowledge improves performance by in a data scarce setting.
References in corpus (11)
- Adam: A Method for Stochastic Optimization
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- Conditional Random Fields as Recurrent Neural Networks
- Deep Learning: A Critical Appraisal
- Neural-Symbolic VQA: Disentangling Reasoning from Vision and Language Understanding
- Harnessing Deep Neural Networks with Logic Rules
- The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- End-to-End Differentiable Proving
- TensorLog: Deep Learning Meets Probabilistic DBs
- Neural Theorem Provers Do Not Learn Rules Without Exploration