Incorporating Domain Knowledge into Deep Neural Networks
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- February 2021
- DOI:
- 10.48550/arXiv.2103.00180
- arXiv:
- arXiv:2103.00180
- Bibcode:
- 2021arXiv210300180D
- Keywords:
-
- Computer Science - Neural and Evolutionary Computing;
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning;
- 68T07 (Primary);
- 68T05;
- 68T01 (Secondary);
- I.2.6;
- I.2.4
- E-Print:
- Submitted to IJCAI-2021 Survey Track (6+2 pages)