Towards Architecture-Agnostic Neural Transfer: A Knowledge-Enhanced Approach

Abstract

The ability to enhance deep representations with prior knowledge is receiving a lot of attention from the AI community as a key enabler to improve the way modern Artificial Neural Networks (ANN) learn. In this paper we introduce our approach to this task, which comprises of a knowledge extraction algorithm, a knowledge injection algorithm and a common intermediate knowledge representation as an alternative to traditional neural transfer. As a result of this research, we envisage a knowledge-enhanced ANN, which will be able to learn, characterise and reuse knowledge extracted from the learning process, thus enabling more robust architecture-agnostic neural transfer, greater explainability and further integration of neural and symbolic approaches to learning.

Cite

Text

Quinn and Mileo. "Towards Architecture-Agnostic Neural Transfer: A Knowledge-Enhanced Approach." International Joint Conference on Artificial Intelligence, 2019. doi:10.24963/IJCAI.2019/915

Markdown

[Quinn and Mileo. "Towards Architecture-Agnostic Neural Transfer: A Knowledge-Enhanced Approach." International Joint Conference on Artificial Intelligence, 2019.](https://mlanthology.org/ijcai/2019/quinn2019ijcai-architecture/) doi:10.24963/IJCAI.2019/915

BibTeX

@inproceedings{quinn2019ijcai-architecture,
  title     = {{Towards Architecture-Agnostic Neural Transfer: A Knowledge-Enhanced Approach}},
  author    = {Quinn, Seán and Mileo, Alessandra},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2019},
  pages     = {6452-6453},
  doi       = {10.24963/IJCAI.2019/915},
  url       = {https://mlanthology.org/ijcai/2019/quinn2019ijcai-architecture/}
}