期刊
KNOWLEDGE-BASED SYSTEMS
卷 222, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.knosys.2021.106989
关键词
Deep learning; Convolutional neural networks; Image classification; Neuro symbolic methods; First-order logic; Learning from constraints
资金
- European Union?s Horizon 2020 research and innovation program [825619]
Deep learning architectures can develop feature representations and classification models in an integrated way during training, and integrating prior knowledge into learning can reduce the amount of required training data.
Deep Learning architectures can develop feature representations and classification models in an integrated way during training. This joint learning process requires large networks with many parameters, and it is successful when a large amount of training data is available. Instead of making the learner develop its entire understanding of the world from scratch from the input examples, the injection of prior knowledge into the learner seems to be a principled way to reduce the amount of require training data, as the learner does not need to induce the rules from the data. This paper presents a general framework to integrate arbitrary prior knowledge into learning. The domain knowledge is provided as a collection of first-order logic (FOL) clauses, where each task to be learned corresponds to a predicate in the knowledge base. The logic statements are translated into a set of differentiable constraints, which can be integrated into the learning process to distill the knowledge into the network, or used during inference to enforce the consistency of the predictions with the prior knowledge. The experimental results have been carried out on multiple image datasets and show that the integration of the prior knowledge boosts the accuracy of several state-of-the-art deep architectures on image classification tasks. (C) 2021 The Authors. Published by Elsevier B.V.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据