eCite Digital Repository

Unsupervised neural-symbolic integration


Tran, SN, Unsupervised neural-symbolic integration, Proceedings of the 2017 International Joint Conference on Artificial Intelligence - Workshop on Explainable AI, 20 August 2017, Melbourne, Australia, pp. 58-62. (2017) [Refereed Conference Paper]

Copyright Statement

Copyright unknown


Symbolic has been long considered as a language of human intelligence while neural networks have advantages of robust computation and dealing with noisy data. The integration of neural-symbolic can offer better learning and reasoning while providing a means for interpretability through the representation of symbolic knowledge. Although previous works focus intensively on supervised feedforward neural networks, little has been done for the unsupervised counterparts. In this paper we show how to integrate symbolic knowledge into unsupervised neural networks. We exemplify our approach with knowledge in different forms, including propositional logic for DNA promoter prediction and first

Item Details

Item Type:Refereed Conference Paper
Research Division:Information and Computing Sciences
Research Group:Artificial intelligence
Research Field:Intelligent robotics
Objective Division:Defence
Objective Group:Defence
Objective Field:Intelligence, surveillance and space
UTAS Author:Tran, SN (Dr Son Tran)
ID Code:140703
Year Published:2017
Deposited By:Information and Communication Technology
Deposited On:2020-09-01
Last Modified:2020-12-18

Repository Staff Only: item control page