Work

A review of some techniques for inclusion of domain-knowledge into deep neural networks

Year: 2022

Type: article

Abstract: We present a survey of ways in which existing scientific knowledge are 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 the inclusion of domain-knowledge by means of changes to: the input, the loss-function, and the architecture of deep networks. The categorisation is for ease of exposition: in practice we expect a combination of such changes will be employed. In each category, we describe techniques that have been shown to yield significant changes in the performance of deep neural networks.

Source: Scientific Reports

DOI: 10.1038/s41598-021-04590-0

Authors: Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan

Institutions: Birla Institute of Technology and Science, Pilani - Goa Campus, Birla Institute of Technology and Science, Pilani

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $2,190

Funders: University of New South Wales, Birla Institute of Technology and Science, Pilani