A Review Of Some Techniques For Inclusion Of Domainknowledge Into Deep Neural Networks

# A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks

**arXiv ID:** 2107.10295
**Authors:** Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan
**Published:** 2021-07-21T18:18:02Z
**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.

## Skill Description

This skill is generated from the arXiv paper: A Review of Some Techniques for Inclusion of Domain-Knowledge into Deep Neural Networks (2107.10295).

## How to Use

[To be filled in by the user or by future automation]

## References

- [arXiv:2107.10295](http://arxiv.org/abs/2107.10295v4)