arXiv (Cornell University) · 2015 · 37 citations · 21 references
ComputingComputer ScienceArtificial IntelligenceKnowledge RepresentationMachine LearningDeep LearningKnowledge AcquisitionKnowledge ModelingNeural NetworksRelation ExtractionRelational Data ModelDomain Knowledge ExtractionGradient DescentNeural Network ClassificationNeural Representation LearningRelation ClassificationRelational ReasoningRule LearningStochastic Gradient Descent
We propose a method combining relational-logic representations with neural network learning. A general lifted architecture, possibly reflecting some background domain knowledge, is described through relational rules which may be handcrafted or learned. The relational rule-set serves as a template for unfolding possibly deep neural networks whose structures also reflect the structures of given training or testing relational examples. Different networks corresponding to different examples share their weights, which co-evolve during training by stochastic gradient descent algorithm. The framework allows for hierarchical relational modeling constructs and learning of latent relational concepts through shared hidden layers weights corresponding to the rules. Discovery of notable relational concepts and experiments on 78 relational learning benchmarks demonstrate favorable performance of the method.
21
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
The Graph Neural Network Model
Franco Scarselli, M. Gori, Ah Chung Tsoi et al. · IEEE Transactions on Neural Networks · 2008 · 9.3K citations · Full text
Matthew Richardson, Pedro Domingos · Machine Learning · 2006 · 2.7K citations · Full text
The Semantics of Predicate Logic as a Programming Language
M. H. van Emden, Robert Kowalski · Journal of the ACM · 1976 · 1.5K citations · Full text
Humanities, Computer Science, Logic +16