EEG data analysis with stacked differentiable neural computers

Ming, Y; Pelusi, D; Fang, CN; Prasad, M; Wang, YK; Wu, D; Lin, CT

EEG data analysis with stacked differentiable neural computers

Ming, Y

Pelusi, D Fang, CN

Prasad, M

Wang, YK

Wu, D Lin, CT

Permalink

Publication Type:: Journal Article
Citation:: Neural Computing and Applications, 2018
Issue Date:: 2018-01-01

Open Access

Copyright Clearance Process

Recently Added
In Progress
Open Access

This item is open access.

Adobe PDF

Download Submitted VersionAdobe PDF (728.81 kB)

View on publisher's site

View statistics

Full metadata record

Field	Value	Language
dc.contributor.author	Ming, Y https://orcid.org/0000-0003-3837-5580	en_US
dc.contributor.author	Pelusi, D	en_US
dc.contributor.author	Fang, CN https://orcid.org/0000-0002-7889-4564	en_US
dc.contributor.author	Prasad, M https://orcid.org/0000-0001-9719-2253	en_US
dc.contributor.author	Wang, YK https://orcid.org/0000-0001-8390-2664	en_US
dc.contributor.author	Wu, D	en_US
dc.contributor.author	Lin, CT https://orcid.org/0000-0001-8371-8197	en_US
dc.date.issued	2018-01-01	en_US
dc.identifier.citation	Neural Computing and Applications, 2018	en_US
dc.identifier.issn	0941-0643	en_US
dc.identifier.uri	http://hdl.handle.net/10453/129275
dc.description.abstract	© 2018, Springer-Verlag London Ltd., part of Springer Nature. Differentiable neural computer (DNC) has demonstrated remarkable capabilities in solving complex problems. In this paper, we propose to stack an enhanced version of differentiable neural computer together to extend its learning capabilities. Firstly, we give an intuitive interpretation of DNC to explain the architectural essence and demonstrate the stacking feasibility by contrasting it with the conventional recurrent neural network. Secondly, the architecture of stacked DNCs is proposed and modified for electroencephalogram (EEG) data analysis. We substitute the original Long Short-Term Memory network controller by a recurrent convolutional network controller and adjust the memory accessing structures for processing EEG topographic data. Thirdly, the practicability of our proposed model is verified by an open-sourced EEG dataset with the highest average accuracy achieved; then after fine-tuning the parameters, we show the minimal mean error obtained on a proprietary EEG dataset. Finally, by analyzing the behavioral characteristics of the trained stacked DNCs model, we highlight the suitableness and potential of utilizing stacked DNCs in EEG signal processing.	en_US
dc.relation	http://purl.org/au-research/grants/arc/DP180100670
dc.relation	http://purl.org/au-research/grants/arc/DP180100656
dc.relation.ispartof	Neural Computing and Applications	en_US
dc.relation.isbasedon	10.1007/s00521-018-3879-1	en_US
dc.subject.classification	Artificial Intelligence & Image Processing	en_US
dc.title	EEG data analysis with stacked differentiable neural computers	en_US
dc.type	Journal Article
utslib.for	0801 Artificial Intelligence and Image Processing	en_US
utslib.for	1702 Cognitive Sciences	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Software
pubs.organisational-group	/University of Technology Sydney/Strength - CAI - Centre for Artificial Intelligence
pubs.organisational-group	/University of Technology Sydney/Students
utslib.copyright.status	open_access
pubs.publication-status	Published	en_US

Abstract:

© 2018, Springer-Verlag London Ltd., part of Springer Nature. Differentiable neural computer (DNC) has demonstrated remarkable capabilities in solving complex problems. In this paper, we propose to stack an enhanced version of differentiable neural computer together to extend its learning capabilities. Firstly, we give an intuitive interpretation of DNC to explain the architectural essence and demonstrate the stacking feasibility by contrasting it with the conventional recurrent neural network. Secondly, the architecture of stacked DNCs is proposed and modified for electroencephalogram (EEG) data analysis. We substitute the original Long Short-Term Memory network controller by a recurrent convolutional network controller and adjust the memory accessing structures for processing EEG topographic data. Thirdly, the practicability of our proposed model is verified by an open-sourced EEG dataset with the highest average accuracy achieved; then after fine-tuning the parameters, we show the minimal mean error obtained on a proprietary EEG dataset. Finally, by analyzing the behavioral characteristics of the trained stacked DNCs model, we highlight the suitableness and potential of utilizing stacked DNCs in EEG signal processing.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/129275