TensorLog: Deep Learning Meets Probabilistic DBs
arXiv:1707.05390
Abstract
We present an implementation of a probabilistic first-order logic called TensorLog, in which classes of logical queries are compiled into differentiable functions in a neural-network infrastructure such as Tensorflow or Theano. This leads to a close integration of probabilistic logical reasoning with deep-learning infrastructure: in particular, it enables high-performance deep learning frameworks to be used for tuning the parameters of a probabilistic logic. Experimental results show that TensorLog scales to problems involving hundreds of thousands of knowledge-base triples and tens of thousands of examples.
References in corpus (7)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Harnessing Deep Neural Networks with Logic Rules
- Differentiable Learning of Logical Rules for Knowledge Base Reasoning
- Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge
- Probabilistic Similarity Logic
- Learning to Compose Neural Networks for Question Answering
- Approximation-Aware Dependency Parsing by Belief Propagation
Cited by in corpus (15)
- Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
- Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge
- Faithful Embeddings for Knowledge Base Queries
- Scalable Neural Methods for Reasoning With a Symbolic Knowledge Base
- Neural Logic Reinforcement Learning
- Learn to Explain Efficiently via Neural Logic Inductive Learning
- Modeling Attention Flow on Graphs
- Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks
- Neural Query Language: A Knowledge Base Query Language for Tensorflow
- A Survey on Neural-symbolic Learning Systems
- NeuralLog: a Neural Logic Language
- A modal aleatoric calculus for probabilistic reasoning: extended version
- SQALER: Scaling Question Answering by Decoupling Multi-Hop and Logical Reasoning
- Differentiable Representations For Multihop Inference Rules
- HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop