Lifted Relational Neural Networks
Lifted Relational Neural Networks
复制标题
提升关系神经网络
DOI：
--
复制
发表时间：
2015
期刊：
影响因子：
--
通讯作者：
Ondřej Kuželka
中科院分区：
文献类型：
--
作者：
Gustav Sourek;Vojtech Aschenbrenner;F. Železný;Ondřej Kuželka
我们提出了一种结合关系逻辑表示和神经网络学习的方法。一个可能反映了一些背景领域知识的通用提升体系结构是通过关系规则来描述的，这些关系规则可能是手工制作的或学习的。关系规则集用作展开可能的深层神经网络的模板，其结构还反映了给定训练或测试关系示例的结构。不同样本对应的不同网络共享权值，权值通过随机梯度下降算法在训练过程中协同进化。该框架允许分层关系建模构造和通过与规则相对应的共享隐藏层权重学习潜在关系概念。显著关系概念的发现和在78个关系学习基准上的实验表明该方法具有良好的性能。
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.
DOI：
--
发表时间：
2012-06
期刊：
Proceedings of the ... International Conference on Machine Learning. International Conference on Machine Learning
影响因子：
--
作者：
Jesse Davis;V. S. Costa;E. Berg;David Page;P. Peissig;Michael Caldwell
通讯作者：
Jesse Davis;V. S. Costa;E. Berg;David Page;P. Peissig;Michael Caldwell