Skip navigation

Hierarchical neural network model with intrinsic timing

Hierarchical neural network model with intrinsic timing

Balisson, Dushan and Melis, Wim J.C. ORCID: 0000-0003-3779-8629 (2016) Hierarchical neural network model with intrinsic timing. In: International Conference on Applied System Innovation 2016. IEEE/Taiwanese Institute of Knowledge Innovation (TIKI), Taiwan, pp. 1-4. ISBN 978-1-4673-9889-3 (doi:https://doi.org/10.1109/ICASI.2016.7539787)

[img]
Preview
PDF (Author Accepted Manuscript)
14758_MELIS_Hierarchical_Neural_Network_2016.pdf - Accepted Version

Download (389kB)
[img] PDF (Extended Abstract - Not for Publication)
14758_MELIS_Extended_Abstract_2016.pdf - Additional Metadata
Restricted to Repository staff only

Download (185kB)
[img] PDF (Email of Acceptance)
14758_MELIS_Acceptance_Email_2016.pdf - Additional Metadata
Restricted to Repository staff only

Download (178kB)

Abstract

In order to overcome some of the challenges that current, conventional computing faces, a large set of research is being performed into unconventional computing platforms, most often inspired by discoveries in neuroscience. This tends to result in Artificial Neural Networks, which are commonly an oversimplified version of their biological equivalent, where various aspects are being ignored, e.g. the aspect of time. This tends to prevent these networks from handling temporal sequences directly in the time domain. Hence, this research studies how the intrinsic timing of a neuron cell can be used to design a hierarchical neural network with feedback. The network is based on a simple Leaky Integrate and Fire RC-model for each neuron where the intrinsic timing is determined by the capacitor discharge. The results show that the model is able to differentiate between temporally different stimuli. Moreover, feedback allows the model to put lower level cells in a predictive state. Finally, the hierarchical model allows for higher-level cells to remain stable for a longer period and therefore allow for a better combination of sequential information at lower levels.

Item Type: Conference Proceedings
Title of Proceedings: International Conference on Applied System Innovation 2016
Additional Information: © 2016 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. 2016 International Conference on Applied System Innovation (ICASI 2016), 27-31 May 2016, Okinawa Convention Center, Japan.
Uncontrolled Keywords: Hierarchical Neural Network, Artificial Neural Network, Intrinsic Timing, Leaky-Integrate and Fire, RC Neuron Modelling
Faculty / School / Research Centre / Research Group: Faculty of Engineering & Science
Faculty of Engineering & Science > School of Engineering (ENG)
Related URLs:
Last Modified: 14 Aug 2017 15:00
URI: http://gala.gre.ac.uk/id/eprint/14758

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year

View more statistics