English

Incorporating Domain Knowledge into Deep Neural Networks

Neural and Evolutionary Computing 2021-03-16 v2 Artificial Intelligence Machine Learning

Abstract

We present a survey of ways in which domain-knowledge has been included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such instances, machine-based model construction may benefit significantly from being provided with human-knowledge of the domain encoded in a sufficiently precise form. This paper examines two broad approaches to encode such knowledge--as logical and numerical constraints--and describes techniques and results obtained in several sub-categories under each of these approaches.

Keywords

Cite

@article{arxiv.2103.00180,
  title  = {Incorporating Domain Knowledge into Deep Neural Networks},
  author = {Tirtharaj Dash and Sharad Chitlangia and Aditya Ahuja and Ashwin Srinivasan},
  journal= {arXiv preprint arXiv:2103.00180},
  year   = {2021}
}

Comments

Submitted to IJCAI-2021 Survey Track (6+2 pages)

R2 v1 2026-06-23T23:33:55.234Z