The Library
Scalable partial explainability in neural networks via flexible activation functions (student abstract)
Tools
Sun, Schyler C., Li, Chen, Wei, Zhuangkun, Tsourdos, Antonios and Guo, Weisi (2021) Scalable partial explainability in neural networks via flexible activation functions (student abstract). In: AAAI Conference on Artificial Intelligence, Online, 02-09 Feb 2021. Published in: Proceedings of the AAAI Conference on Artificial Intelligence, 35 (18). pp. 15899-15900. ISBN 9781577358664. ISSN 2374-3468.
Research output not available from this repository.
Request-a-Copy directly from author or use local Library Get it For Me service.
Official URL: https://ojs.aaai.org/index.php/AAAI/article/view/1...
Abstract
Current state-of-the-art neural network explanation methods (e.g. Saliency maps, DeepLIFT, LIME, etc.) focus more on the direct relationship between NN outputs and inputs rather than the NN structure and operations itself, hence there still exists uncertainty over the exact role played by neurons. In this paper, we propose a novel neural network structure with Kolmogorov-Arnold Superposition Theorem based topology and Gaussian Processes based flexible activation function to achieve partial explainability of the neuron inner reasoning. The model feasibility is verified in a case study on binary classification of the banknotes.
Item Type: | Conference Item (Paper) | ||||
---|---|---|---|---|---|
Divisions: | Faculty of Science, Engineering and Medicine > Engineering > Engineering | ||||
Journal or Publication Title: | Proceedings of the AAAI Conference on Artificial Intelligence | ||||
Publisher: | AAAI Press | ||||
ISBN: | 9781577358664 | ||||
ISSN: | 2374-3468 | ||||
Official Date: | 18 May 2021 | ||||
Dates: |
|
||||
Volume: | 35 | ||||
Number: | 18 | ||||
Page Range: | pp. 15899-15900 | ||||
Status: | Peer Reviewed | ||||
Publication Status: | Published | ||||
Access rights to Published version: | Restricted or Subscription Access | ||||
Copyright Holders: | Association for the Advancement of Artificial Intelligence | ||||
Conference Paper Type: | Paper | ||||
Title of Event: | AAAI Conference on Artificial Intelligence | ||||
Type of Event: | Conference | ||||
Location of Event: | Online | ||||
Date(s) of Event: | 02-09 Feb 2021 | ||||
Related URLs: |
Request changes or add full text files to a record
Repository staff actions (login required)
View Item |